Principal Engineer (Agentic Products & Workflows)

Join Big Viking Games as a Principal Engineer, Agentic Products & Workflows. In this founding-level engineering role, you will architect and build the systems that drive our AI transformation. You will own the agentic platform end to end, including orchestration primitives, workflow design, review loops, memory, evaluation, observability, and integration into live-game systems. This is a unique opportunity to shape the future of game development in an AI-first environment.

• Architect and build the agentic platform, autonomous engineering workflows, AI-enabled content pipelines, review systems, integration layers, and observability infrastructure.
• Own verticals end to end, including architecture, orchestration, data models, backend services, APIs, evaluation loops, human review surfaces, observability, quality controls, and the production workflows teams use every day.
• Drive reliability and observability as a first-class product surface, ensuring that the system misbehaves is detected before anyone else does.

• Agentic systems you have designed, built, shipped, or operated
• Evidence that other people’s output improved because of infrastructure, tools, workflows, or platforms you built
• Experience with orchestration, tool use, task planning, state management, context management, retrieval, workflow reliability, and human review systems
• Strong first-principles engineering judgment. You can defend your architecture choices without hiding behind a framework
• If that problem excites you, this role is built for you
• When you interview with us, expect to show real systems, not just talk about AI
• Real experience building agentic systems, autonomous workflows, AI-enabled products, or production AI infrastructure
• Experience building or operating evals, traces, guardrails, test harnesses, quality checks, or other systems that make AI output measurable and trustworthy
• High agency, high urgency, and a builder’s mindset. You move fast without confusing speed with sloppiness
• Daily, fluent use of AI coding agents such as Claude Code, Cursor, Codex, or similar tools as part of how you work
• Systems that run when you are away from the keyboard and the instrumentation to trust them
• Experience with eval suites, regression tests, quality measurement, observability, and production monitoring for AI systems
• Disciplined git, pull request, code review, testing, deployment, and production operations practices, whether the author is human or agent
• Clear judgment about where AI can automate work, where human review is required, and where quality cannot be compromised
• Experience with structured generation, tool calls, function calling, schema-constrained output, approval workflows, and automated review
• Substantial experience shipping and operating production software at scale
• A high bar for reliability, maintainability, observability, documentation, and developer experience
• Understanding of model behavior, including context windows, retrieval failure modes, grounding gaps, hallucination patterns, calibration, prompt design, and spec design
• Comfort with nondeterministic systems, ambiguous requirements, and failures that require deep investigation across unfamiliar stacks
• Experience owning products, platforms, or systems end to end, not just one layer of someone else’s stack
• Ability to mentor other engineers, set patterns, and raise the technical bar around you
• Strong full stack engineering depth, ideally with TypeScript, Node.js, React, Next.js, SQL, Postgres, APIs, backend services, queues, workers, and production web applications
• Practical fluency with AI coding agents and multi-agent workflows
• Strong product judgment and the ability to identify when generated output is wrong, incomplete, fragile, off-brand, unsafe, or subtly low quality
• The ideal candidate is a principal-level builder who wants the ground floor of something consequential
• They are not using AI simply to write code faster
• They can think through the product experience, the data model, the workflow, the orchestration pattern, the interface, the failure modes, the quality controls, and the production risks, then go build the system
• They are comfortable with ambiguity, but they do not leave ambiguity unmanaged
• They are architecting the systems that AI runs inside: orchestration, tools, memory, evals, review loops, observability, calibration, recovery, and human control surfaces
• They turn unclear goals into executable specs. They turn experiments into platforms
• They have a high bar, a practical bias, and something to prove
• They turn repeated manual effort into automated workflows. They turn AI demos into production infrastructure
• This role is best suited for someone who wants founding-level ownership of a meaningful AI platform inside a profitable live-service gaming company, and who is excited to help define how game content, engineering workflows, and autonomous systems are built for the next decade
• Experience in gaming, live-service products, virtual worlds, social games, free-to-play games, high-DAU consumer products, or other production environments where reliability and quality matter every day
• Experience with tool orchestration, agent memory, multi-model routing, background workers, queues, event-driven systems, workflow engines, or durable execution
• Zero-to-one, founding-engineer, or early-stage platform-building experience
• Experience with observability tools, distributed-systems reliability, incident response, cost telemetry, or production platform operations
• Experience shipping generative AI or agentic AI features in customer-facing or business-critical production environments
• Experience with MCP, OpenAI, Anthropic, Gemini, Vercel AI SDK, LangGraph, LlamaIndex, LangChain, or similar AI development ecosystems
• Experience building internal tools for creative production, game operations, content pipelines, asset generation, QA automation, or media workflows
• Experience with art, animation, asset pipelines, Flash, Animate, or creative tooling
• Strong visual judgment and the ability to push generated content toward better quality, consistency, and production value