About The Role

Design, build, and enhance AI-powered applications and backend services for internal or customer-facing use cases.
Build and maintain AI agents and agentic workflows that can reason, orchestrate tasks, and integrate with external tools and services.
Develop MCP-based integrations and tool interfaces that enable AI systems to interact securely with external platforms, APIs, and business systems.
Implement prompt orchestration, context handling, tool calling, memory patterns, and evaluation workflows to improve agent reliability.
Collaborate with engineering, product, and architecture teams to define scalable patterns for AI agent development and deployment.
Integrate LLM capabilities into software systems while balancing performance, reliability, cost, and safety.
Investigate system issues, improve quality and observability, and optimize AI workflow efficiency in production environments.
Participate in code reviews, release support, experimentation, and production incident resolution.
Create technical documentation and contribute to best practices for AI engineering, agent development, and MCP adoption.

4+ years of experience in software engineering, backend engineering, or applied AI engineering.
Strong programming skills in Java and/or Python.
Hands-on experience building AI-powered applications or integrating LLM capabilities into production systems.
Experience designing or building AI agents, multi-step orchestration workflows, or tool-using automation systems.
Experience with MCP or similar integration patterns for connecting AI systems to external tools, APIs, or enterprise platforms.
Strong understanding of system design, APIs, distributed systems, and production software engineering fundamentals.
Familiarity with prompt design, context management, evaluation approaches, and reliability patterns for agent-based systems.
Proven ability to work effectively in fast-paced delivery environments.
Delivery-oriented and comfortable operating across development, experimentation, and production support responsibilities.
Effective at collaborating with cross-functional teams under tight timelines.
Strong ownership mindset with practical problem-solving skills.

Experience with multi-agent systems, retrieval-augmented generation, semantic search, or vector-based architectures.
Familiarity with cloud-native infrastructure, monitoring, and observability for AI services.
Experience with model evaluation, guardrails, safety patterns, and prompt/version lifecycle management.
Experience integrating AI solutions with enterprise platforms such as Salesforce, Jira, Slack, or internal developer tools.
Background in workflow automation, event-driven systems, or backend platforms that support AI-enabled products.

Java and/or Python.
MCP or similar AI integration patterns for connecting AI systems with external tools, APIs, or platforms.
LLM and agent-based application environments supporting prompt orchestration, context handling, tool calling, memory, and evaluation.
APIs and production backend or distributed systems.

Remote contract engagement.
100% allocation, approximately 40 hours per week.
Candidates must be based in APAC or LATAM.
Candidates must be able to provide working-hours overlap with U.S. Central Time.
APAC candidates should also be able to provide some overlap with India Standard Time, with availability preferably extending through 11:00 a.m. U.S. Central Time.
Current engagement end date: March 31, 2027.