AI Engineer at NetBrain — Toronto, Canada

About The Role

&lt;div class=&quot;content-intro&quot;&gt;&lt;p class=&quot;MsoNormal&quot; style=&quot;margin-bottom: 12.0pt;&quot;&gt;&lt;span style=&quot;font-size: 10pt; font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; color: black;&quot;&gt;Founded in 2004, NetBrain is the leader in no-code network automation. Its ground-breaking Next-Gen platform provides IT operations teams with the ability to scale their hybrid multi-cloud connected networks by automating the processes associated with Diagnostic Troubleshooting, Outage Prevention and Protected Change Management. &amp;nbsp;Today, over 2,500 of the world’s largest enterprises and managed services providers leverage NetBrain’s platform.&lt;/span&gt;&lt;/p&gt;&lt;/div&gt;&lt;p&gt;&lt;span style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 14pt;&quot;&gt;&lt;em&gt;&lt;strong&gt;What We Need&lt;/strong&gt;&lt;/em&gt;&lt;/span&gt;&lt;/p&gt;
&lt;p&gt;&lt;span style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;We’re looking for a Senior AI Engineer to design and build production-grade agent and RAG systems that power intelligent, reliable automation across our platform. This role combines hands-on engineering with system-level thinking—owning everything from architecture and evaluation to scalability, observability, and reliability in production. The ideal candidate thrives in ambiguity, moves quickly from prototype to production, and brings a strong focus on quality, safety, and real-world impact.&lt;/span&gt;&lt;/p&gt;
&lt;p&gt;&amp;nbsp;&lt;/p&gt;
&lt;p&gt;&lt;span style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 14pt;&quot;&gt;&lt;em&gt;&lt;strong&gt;What You&#39;ll Do&lt;/strong&gt;&lt;/em&gt;&lt;/span&gt;&lt;/p&gt;
&lt;p class=&quot;p1&quot;&gt;&lt;span style=&quot;font-size: 12pt;&quot;&gt;&lt;strong&gt;&lt;span style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif;&quot;&gt;Agent Platform Architecture&lt;/span&gt;&lt;/strong&gt;&lt;/span&gt;&lt;/p&gt;
&lt;ul&gt;
&lt;li class=&quot;p1&quot; style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;&lt;span style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;Design and implement core capabilities for an enterprise-grade Agent platform, including orchestration patterns such as ReAct, Plan-and-&lt;/span&gt;&lt;/li&gt;
&lt;li class=&quot;p1&quot; style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;&lt;span style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;Execute, and Supervisor, as well as tool execution, context and memory management, and safety guardrails.&lt;/span&gt;&lt;/li&gt;
&lt;li class=&quot;p1&quot; style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;&lt;span style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;Design enterprise-grade Agent execution and governance mechanisms, including Human-in-the-Loop approval workflows, multi-tenant&lt;/span&gt;&lt;/li&gt;
&lt;li class=&quot;p1&quot; style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;&lt;span style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;permission isolation, policy enforcement, and secure execution controls.&lt;/span&gt;&lt;/li&gt;
&lt;li class=&quot;p1&quot; style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;&lt;span style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;Build reusable Agent Skills, standardized tool interfaces, and a scalable tool ecosystem deeply integrated with NetBrain platform&lt;/span&gt;&lt;/li&gt;
&lt;li class=&quot;p1&quot; style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;&lt;span style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;capabilities and business workflows.&lt;/span&gt;&lt;/li&gt;
&lt;/ul&gt;
&lt;p class=&quot;p1&quot;&gt;&lt;span style=&quot;font-size: 12pt;&quot;&gt;&lt;strong&gt;&lt;span style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif;&quot;&gt;LLM and Model Optimization&lt;/span&gt;&lt;/strong&gt;&lt;/span&gt;&lt;/p&gt;
&lt;ul&gt;
&lt;li class=&quot;p1&quot; style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;&lt;span style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;Design and implement LLM post-training strategies, including domain-specific Supervised Fine-Tuning (SFT), DPO/RLHF-based&lt;/span&gt;&lt;/li&gt;
&lt;li class=&quot;p1&quot; style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;&lt;span style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;preference alignment, and parameter-efficient fine-tuning techniques such as LoRA, to continuously improve model performance in the&lt;/span&gt;&lt;/li&gt;
&lt;li class=&quot;p1&quot; style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;&lt;span style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;network operations domain.&lt;/span&gt;&lt;/li&gt;
&lt;li class=&quot;p1&quot; style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;&lt;span style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;Build an Agent self-learning feedback loop that converts production execution traces, user feedback, and evaluation results into high-&lt;/span&gt;&lt;/li&gt;
&lt;li class=&quot;p1&quot; style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;&lt;span style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;quality datasets for continuously improving prompts, skills, models, and retrieval strategies.&lt;/span&gt;&lt;/li&gt;
&lt;li class=&quot;p1&quot; style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;&lt;span style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;Analyze and optimize LLM behavior across areas such as instruction following, tool calling, structured output generation, contextual&lt;/span&gt;&lt;/li&gt;
&lt;li class=&quot;p1&quot; style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;&lt;span style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;understanding, reasoning stability, and hallucination mitigation.&lt;/span&gt;&lt;/li&gt;
&lt;/ul&gt;
&lt;p class=&quot;p1&quot;&gt;&lt;span style=&quot;font-size: 12pt;&quot;&gt;&lt;strong&gt;&lt;span style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif;&quot;&gt;Evaluation, Reliability, and Observability&lt;/span&gt;&lt;/strong&gt;&lt;/span&gt;&lt;/p&gt;
&lt;ul&gt;
&lt;li class=&quot;p1&quot; style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;&lt;span style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;Build production-grade LLM and Agent evaluation frameworks and automated regression pipelines, including benchmark datasets,&lt;/span&gt;&lt;/li&gt;
&lt;li class=&quot;p1&quot; style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;&lt;span style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;deterministic checks, LLM-as-a-Judge, tool-call validation, retrieval-quality evaluation, and end-to-end task success metrics.&lt;/span&gt;&lt;/li&gt;
&lt;li class=&quot;p1&quot; style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;&lt;span style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;Establish release quality gates and hallucination-detection mechanisms for AI features to prevent significant accuracy, reliability, and&lt;/span&gt;&lt;/li&gt;
&lt;li class=&quot;p1&quot; style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;&lt;span style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;performance regressions from reaching production.&lt;/span&gt;&lt;/li&gt;
&lt;li class=&quot;p1&quot; style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;&lt;span style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;Build comprehensive AI system observability capabilities, including distributed tracing, structured logging, metrics, dashboards, and&lt;/span&gt;&lt;/li&gt;
&lt;li class=&quot;p1&quot; style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;&lt;span style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;alerting.&lt;/span&gt;&lt;/li&gt;
&lt;li class=&quot;p1&quot; style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;&lt;span style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;Rapidly diagnose and resolve production AI failures, including hallucinations, incorrect tool selection, invalid tool parameters, Agent&lt;/span&gt;&lt;/li&gt;
&lt;li class=&quot;p1&quot; style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;&lt;span style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;loops, retrieval-quality degradation, structured-output failures, latency regressions, and unexpected model behavior changes.&lt;/span&gt;&lt;/li&gt;
&lt;/ul&gt;
&lt;p class=&quot;p1&quot;&gt;&lt;span style=&quot;font-size: 12pt;&quot;&gt;&lt;strong&gt;&lt;span style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif;&quot;&gt;Production Engineering and Technical Execution&lt;/span&gt;&lt;/strong&gt;&lt;/span&gt;&lt;/p&gt;
&lt;ul&gt;
&lt;li class=&quot;p1&quot; style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;&lt;span style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;Design and implement highly reliable backend services for production AI and Agent workloads, including asynchronous and concurrent&lt;/span&gt;&lt;/li&gt;
&lt;li class=&quot;p1&quot; style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;&lt;span style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;processing, retries, timeouts, caching, rate limiting, and fault isolation.&lt;/span&gt;&lt;/li&gt;
&lt;li class=&quot;p1&quot; style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;&lt;span style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;Continuously optimize latency, throughput, token consumption, and infrastructure cost to meet platform SLA requirements and support&lt;/span&gt;&lt;/li&gt;
&lt;li class=&quot;p1&quot; style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;&lt;span style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;large-scale production workloads.&lt;/span&gt;&lt;/li&gt;
&lt;li class=&quot;p1&quot; style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;&lt;span style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;Independently diagnose and resolve complex AI system issues spanning prompts, models, RAG, tools, Agent workflows, backend&lt;/span&gt;&lt;/li&gt;
&lt;li class=&quot;p1&quot; style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;&lt;span style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;services, and infrastructure.&lt;/span&gt;&lt;/li&gt;
&lt;li class=&quot;p1&quot; style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;&lt;span style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;Lead technical design for critical modules and system-level capabilities, ensuring solutions align with platform architecture, security&lt;/span&gt;&lt;/li&gt;
&lt;li class=&quot;p1&quot; style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;&lt;span style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;requirements, engineering standards, and product requirements.&lt;/span&gt;&lt;/li&gt;
&lt;li class=&quot;p1&quot; style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;&lt;span style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;Drive technical improvements based on production data, evaluation results, and benchmarks, and collaborate closely with Engineering,&lt;/span&gt;&lt;/li&gt;
&lt;li class=&quot;p1&quot; style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;&lt;span style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;Product, QA, and other teams to deliver solutions into production.&lt;/span&gt;&lt;/li&gt;
&lt;/ul&gt;
&lt;p class=&quot;p1&quot;&gt;&lt;span style=&quot;font-size: 12pt;&quot;&gt;&lt;strong&gt;&lt;span style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif;&quot;&gt;Applied Research and Technical Strategy&lt;/span&gt;&lt;/strong&gt;&lt;/span&gt;&lt;/p&gt;
&lt;ul&gt;
&lt;li class=&quot;p1&quot; style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;&lt;span style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;Prototype, benchmark, and productionize emerging technologies such as GraphRAG, Knowledge Graphs, MCP, LLM Post-Training, and&lt;/span&gt;&lt;/li&gt;
&lt;li class=&quot;p1&quot; style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;&lt;span style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;Agent Self-Learning to improve grounding, multi-hop reasoning, and domain expertise.&lt;/span&gt;&lt;/li&gt;
&lt;li class=&quot;p1&quot; style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;&lt;span style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;Continuously evaluate Agent frameworks and supporting infrastructure, including LangChain, LangGraph, AutoGen, and LlamaIndex,&lt;/span&gt;&lt;/li&gt;
&lt;li class=&quot;p1&quot; style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;&lt;span style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;and provide technical recommendations for platform architecture evolution and product technology strategy.&lt;/span&gt;&lt;/li&gt;
&lt;li class=&quot;p1&quot; style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;&lt;span style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;Stay current with developments in LLM and Agent technologies and rapidly translate promising technologies into measurable, testable,&lt;/span&gt;&lt;/li&gt;
&lt;li class=&quot;p1&quot; style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;&lt;span style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;and production-ready engineering capabilities.&lt;/span&gt;&lt;/li&gt;
&lt;/ul&gt;
&lt;p class=&quot;p2&quot;&gt;&lt;span style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif;&quot;&gt;&lt;em&gt;&lt;strong&gt;&lt;span style=&quot;font-size: 14pt;&quot;&gt;What You Bring&lt;/span&gt;&lt;/strong&gt;&lt;/em&gt;&lt;/span&gt;&lt;/p&gt;
&lt;ul&gt;
&lt;li class=&quot;p1&quot; style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;&lt;span style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;Bachelor&#39;s degree or higher in Computer Science, Artificial Intelligence, Electrical Engineering, or a related technical field. Master&#39;s or Ph.D.&lt;/span&gt;&lt;/li&gt;
&lt;li class=&quot;p1&quot; style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;&lt;span style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;preferred; equivalent practical experience will also be considered.&lt;/span&gt;&lt;/li&gt;
&lt;li class=&quot;p1&quot; style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;&lt;span style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;3+ years of experience in software engineering, machine learning, or applied AI, including 2+ years building, deploying, and operating production-&lt;/span&gt;&lt;/li&gt;
&lt;li class=&quot;p1&quot; style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;&lt;span style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;grade LLM or Agent applications. Must have delivered at least one LLM-powered feature end-to-end and owned its ongoing operation and&lt;/span&gt;&lt;/li&gt;
&lt;li class=&quot;p1&quot; style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;&lt;span style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;improvement after production launch.&lt;/span&gt;&lt;/li&gt;
&lt;li class=&quot;p1&quot; style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;&lt;span style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;Deep understanding of Agent architectures and LLM behavioral characteristics, including instruction following, tool-calling behavior, and context&lt;/span&gt;&lt;/li&gt;
&lt;li class=&quot;p1&quot; style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;&lt;span style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;sensitivity, with hands-on experience building multi-step workflows involving reasoning, tool execution, state management, structured outputs,&lt;/span&gt;&lt;/li&gt;
&lt;li class=&quot;p1&quot; style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;&lt;span style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;validation, and error recovery.&lt;/span&gt;&lt;/li&gt;
&lt;li class=&quot;p1&quot; style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;&lt;span style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;Proven ability to diagnose and resolve production LLM/Agent failures, including hallucinations, incorrect tool calls, retrieval-quality degradation,&lt;/span&gt;&lt;/li&gt;
&lt;li class=&quot;p1&quot; style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;&lt;span style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;Agent loops, structured-output failures, latency regressions, and regressions introduced by prompt or model changes.&lt;/span&gt;&lt;/li&gt;
&lt;li class=&quot;p1&quot; style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;&lt;span style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;Strong Python and distributed backend engineering skills, including API and service development, asynchronous and concurrent programming,&lt;/span&gt;&lt;/li&gt;
&lt;li class=&quot;p1&quot; style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;&lt;span style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;retries, timeouts, caching, rate limiting, testing, logging, and cross-service performance debugging.&lt;/span&gt;&lt;/li&gt;
&lt;li class=&quot;p1&quot; style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;&lt;span style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;Hands-on experience designing evaluation systems for LLM applications, including dataset construction, metric definition, regression testing, and&lt;/span&gt;&lt;/li&gt;
&lt;li class=&quot;p1&quot; style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;&lt;span style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;release quality gates.&lt;/span&gt;&lt;/li&gt;
&lt;li class=&quot;p1&quot; style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;&lt;span style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;Strong understanding of security risks associated with LLM and Agent applications, including prompt injection, data leakage, unsafe tool&lt;/span&gt;&lt;/li&gt;
&lt;li class=&quot;p1&quot; style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;&lt;span style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;execution, permission boundaries, and uncontrolled Agent autonomy.&lt;/span&gt;&lt;/li&gt;
&lt;li class=&quot;p1&quot; style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;&lt;span style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;Ability to independently design, implement, debug, deploy, and operate complex production systems.&lt;/span&gt;&lt;/li&gt;
&lt;/ul&gt;
&lt;p class=&quot;p2&quot;&gt;&lt;span style=&quot;font-size: 12pt;&quot;&gt;&lt;strong&gt;&lt;span style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif;&quot;&gt;Preferred Qualifications&lt;/span&gt;&lt;/strong&gt;&lt;/span&gt;&lt;/p&gt;
&lt;ul&gt;
&lt;li class=&quot;p1&quot; style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;&lt;span style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;Strong experience with RAG and advanced retrieval systems, including embeddings, vector and hybrid search, reranking, chunking strategies,&lt;/span&gt;&lt;/li&gt;
&lt;li class=&quot;p1&quot; style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;&lt;span style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;grounding and citation mechanisms, as well as multi-hop retrieval, Knowledge Graphs, or GraphRAG.&lt;/span&gt;&lt;/li&gt;
&lt;li class=&quot;p1&quot; style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;&lt;span style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;Familiarity with Agent frameworks such as LangGraph, LangChain, AutoGen, and LlamaIndex, as well as standardized protocols such as MCP&lt;/span&gt;&lt;/li&gt;
&lt;li class=&quot;p1&quot; style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;&lt;span style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;(Model Context Protocol) for connecting Agents with external tools and systems. A strong understanding of the underlying architecture is more&lt;/span&gt;&lt;/li&gt;
&lt;li class=&quot;p1&quot; style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;&lt;span style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;important than expertise in any specific framework.Experience designing Agent runtime mechanisms, including Human-in-the-Loop workflows such as risk classification, approval, interruption, pause&lt;/span&gt;&lt;/li&gt;
&lt;li class=&quot;p1&quot; style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;&lt;span style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;/resume, as well as context management for long-running Agent workflows, including state persistence, history compression, and memory&lt;/span&gt;&lt;/li&gt;
&lt;li class=&quot;p1&quot; style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;&lt;span style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;systems.&lt;/span&gt;&lt;/li&gt;
&lt;li class=&quot;p1&quot; style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;&lt;span style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;Experience with LangSmith or similar LLM observability and evaluation platforms.&lt;/span&gt;&lt;/li&gt;
&lt;li class=&quot;p1&quot; style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;&lt;span style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;Experience with LLM fine-tuning, including LoRA or other parameter-efficient fine-tuning techniques.&lt;/span&gt;&lt;/li&gt;
&lt;li class=&quot;p1&quot; style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;&lt;span style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;Experience applying LLM technologies to networking, infrastructure, cybersecurity, observability, or other complex technical domains.&lt;/span&gt;&lt;/li&gt;
&lt;li class=&quot;p1&quot; style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;&lt;span style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;Fluent in both English and Chinese, with strong cross-regional communication and collaboration skills.&lt;/span&gt;&lt;/li&gt;
&lt;/ul&gt;
&lt;p&gt;&amp;nbsp;&lt;/p&gt;
&lt;p&gt;&lt;span style=&quot;font-size: 14pt; font-family: &#39;trebuchet ms&#39;, geneva, sans-serif;&quot;&gt;&lt;strong&gt;&lt;em&gt;What We Offer&lt;/em&gt;&lt;/strong&gt;&lt;/span&gt;&lt;/p&gt;
&lt;p&gt;&lt;span style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 12pt;&quot;&gt;Our comprehensive compensation package is vital in how we recognize our people for the impact they make on us reaching our goals as a company.&lt;/span&gt;&lt;/p&gt;
&lt;p&gt;&lt;span style=&quot;font-size: 12pt; font-family: &#39;trebuchet ms&#39;, geneva, sans-serif;&quot;&gt;For this role, the estimated base is CAD $130,000 - CAD $165,000 + Bonus. The actual salary may vary based on a range of factors, including market and individual qualifications objectively assessed during the interview process.&lt;/span&gt;&lt;/p&gt;
&lt;p&gt;&lt;span style=&quot;font-size: 12pt; font-family: &#39;trebuchet ms&#39;, geneva, sans-serif;&quot;&gt;The range listed above is a guideline and may be modified. People Experience offers a comprehensive benefits package in addition to cash compensation that includes but is not limited to RRSP and medical/dental coverage. Speak with your Recruiter for more details on our Total Rewards philosophy.&lt;br&gt;&lt;br&gt;#LI-BW1&lt;/span&gt;&lt;/p&gt;
&lt;p&gt;&amp;nbsp;&lt;/p&gt;&lt;div class=&quot;content-conclusion&quot;&gt;&lt;p&gt;&lt;span style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 10pt;&quot;&gt;NetBrain invites all interested and qualified candidates to apply for employment opportunities.&lt;/span&gt;&lt;/p&gt;
&lt;p&gt;&lt;span style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 10pt;&quot;&gt;Qualified applicants will receive consideration for employment without regard to race, color, religion, sex, national origin, disability, protected veteran status, or other characteristics protected by law.&lt;/span&gt;&lt;/p&gt;
&lt;p&gt;&lt;span style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 10pt;&quot;&gt;If you have a disability that prevents or limits your ability to use or access the site, or if you require any other accommodation in the application process due to a disability, you may request a reasonable accommodation. To make a request, please contact our People Team at:&amp;nbsp;&lt;a href=&quot;mailto:[email hidden]&quot;&gt;[email hidden]&lt;/a&gt;&amp;nbsp;and we will be happy to assist you.&lt;/span&gt;&lt;/p&gt;
&lt;p&gt;&lt;span style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 10pt;&quot;&gt;In compliance with applicable laws, NetBrain conducts holistic, individual background reviews in support of all hiring decisions.&lt;/span&gt;&lt;/p&gt;
&lt;p&gt;&lt;span style=&quot;font-family: &#39;trebuchet ms&#39;, geneva, sans-serif; font-size: 10pt;&quot;&gt;It is unlawful in Massachusetts to require or administer a lie detector test as a condition of employment or continued employment. An employer who violates this law shall be subject to criminal penalties and civil liability.&lt;/span&gt;&lt;/p&gt;
&lt;p&gt;&amp;nbsp;&lt;/p&gt;&lt;/div&gt;