Principal Engineer, Agentic Products & Workflows

Principal Engineer, Agentic Products & Workflows

Toronto, ON

Hybrid, 4 days per week in office

Full-time

Department: Engineering

Reports to: Engineering and Studio Leadership

About Big Viking Games

Big Viking Games exists to make fans.

We are a profitable, independent Canadian gaming company focused on building, operating, and growing long-standing online game communities. Our flagship titles, YoWorld and FishWorld, have entertained millions of players over their lifetime. These are enduring live-service virtual worlds with rich in-game economies, virtual goods, deep social interaction, and player communities measured in years, not sessions.

We are now rebuilding the company as an AI-first studio. That is not a slogan here. It is an operating standard.

AI agents are already changing how we build, test, review, produce, and operate. We believe a small team of exceptional builders, amplified by well-architected AI systems, can outperform teams many times larger. This role exists to help prove that, operationalize it, and define what the next generation of game development looks like.

About the Role

Big Viking Games is hiring a Principal Engineer, Agentic Products & Workflows to build the systems that make an AI-first game studio real.

This is a founding-level engineering seat at the center of our AI transformation. You will help architect and build the agentic platform, autonomous engineering workflows, AI-enabled content pipelines, review systems, integration layers, and observability infrastructure that allow agents to produce reliable, reviewable, production-grade output for live games.

This is not a role for someone who is simply curious about AI.

You should already be building with agents, shipping systems, testing workflows, using AI coding tools daily, and developing opinions from real production experience. We care less about pedigree and more about what you have built, how you think, and whether your systems survive contact with real users, real content, real revenue, and real production constraints.

You will own verticals end to end: architecture, orchestration, data models, backend services, APIs, evaluation loops, human review surfaces, observability, quality controls, and the production workflows teams use every day.

This is hard in a very specific way. Agentic systems are nondeterministic, tool-driven, context-dependent, and often operating with minimal supervision. When they fail, they can fail quietly, expensively, or at the wrong moment. Your job is to build the infrastructure that makes those systems legible, reliable, recoverable, and trusted.

If that problem excites you, this role is built for you.

What You’ll Build

You will build and own systems across two flagship workstreams.

Autonomous Engineering Platform

The internal platform that lets a small number of engineers safely direct a large amount of autonomous work.

This includes:

• Orchestration primitives for multi-agent, multi-model workflows, including routing, scheduling, state management, memory, task decomposition, and recovery.
• Autonomous engineering workflows that can take a scoped ticket toward a reviewed, tested pull request.
• AI-to-AI review layers where agents critique, test, validate, and gate each other’s output before a human needs to intervene.
• Self-healing workflows with retries, escalation paths, rollback, recovery, and failure classification.
• Cross-agent memory and calibration systems so knowledge compounds instead of disappearing between runs.
• Prediction and confidence systems that help agents know when to proceed, when to ask, and when to stop.
• Evaluation infrastructure, test harnesses, traces, metrics, and dashboards that catch hallucinations, regressions, grounding gaps, quality drift, and cost spikes before they reach production.
• Integration layers that connect agents safely to codebases, tickets, repositories, data sources, tools, documentation, and production workflows.

LiveOps Content Pipelines

The AI-enabled production systems that turn creative direction into production-ready game content at scale.

This includes:

• Content generation workflows that produce structured, reviewable output aligned to YoWorld, FishWorld, and our quality standards.
• Human review surfaces where designers, artists, product managers, and live operations teams can steer, approve, reject, revise, and improve generated content.
• Prompt and spec composition systems that make quality repeatable rather than dependent on individual heroics.
• Audit, retry, versioning, and approval infrastructure so every input, output, revision, decision, and release step is tracked and recoverable.
• Tooling that helps creative and production teams move faster without lowering the bar.
• Integration layers that move approved content safely into live game workflows.

You will own the quality of what these systems produce, not just the plumbing that moves data around.

What You’ll Do

• Architect, build, test, and operate agentic systems that support AI-enabled game production, autonomous engineering, content workflows, and internal tools.
• Own the agentic platform end to end, including orchestration primitives, workflow design, review loops, memory, evaluation, observability, and integration into live-game systems.
• Choose and defend the right orchestration pattern for each problem, including sequential, parallel, swarm, planner-executor, tool-using, and human-in-the-loop patterns.
• Build systems where agents can safely use tools, call APIs, interact with repositories, retrieve context, modify assets, generate structured outputs, and escalate when they should not proceed.
• Design guardrails, validation layers, eval suites, review gates, approval flows, and recovery paths that keep autonomous output at production quality.
• Build human-in-the-loop systems that preserve human judgment where it matters without turning every workflow into manual review.
• Drive reliability and observability as a first-class product surface. If the system misbehaves, you should know before anyone else does.
• Ship against outcomes that matter: cost per asset, quality and rework rate, throughput, review speed, placement speed, escaped-defect rate, uptime, and production trust.
• Translate ambiguous creative, operational, and engineering goals into clear specifications, scoped plans, and shipped systems.
• Partner directly with creative AI, engineering, product, design, art, live operations, QA, and leadership to find the highest-leverage problems and solve them.
• Make our codebases, tools, documentation, and workflows more legible to both humans and agents.
• Set the engineering bar for agentic development at BVG through architecture, review standards, documentation, patterns, and mentorship.
• Use AI coding agents as a core part of your daily workflow, directing them, reviewing their output, and building infrastructure that makes them more useful for everyone.
• Help define a practical AI-first engineering culture focused on speed, quality, reliability, and measurable business impact.

Requirements

What You Bring

• Substantial experience shipping and operating production software at scale.
• Strong full stack engineering depth, ideally with TypeScript, Node.js, React, Next.js, SQL, Postgres, APIs, backend services, queues, workers, and production web applications.
• Experience owning products, platforms, or systems end to end, not just one layer of someone else’s stack.
• Real experience building agentic systems, autonomous workflows, AI-enabled products, or production AI infrastructure.
• Daily, fluent use of AI coding agents such as Claude Code, Cursor, Codex, or similar tools as part of how you work.
• Strong first-principles engineering judgment. You can defend your architecture choices without hiding behind a framework.
• Experience with orchestration, tool use, task planning, state management, context management, retrieval, workflow reliability, and human review systems.
• Experience building or operating evals, traces, guardrails, test harnesses, quality checks, or other systems that make AI output measurable and trustworthy.
• Comfort with nondeterministic systems, ambiguous requirements, and failures that require deep investigation across unfamiliar stacks.
• Strong product judgment and the ability to identify when generated output is wrong, incomplete, fragile, off-brand, unsafe, or subtly low quality.
• A high bar for reliability, maintainability, observability, documentation, and developer experience.
• Disciplined git, pull request, code review, testing, deployment, and production operations practices, whether the author is human or agent.
• Ability to mentor other engineers, set patterns, and raise the technical bar around you.
• High agency, high urgency, and a builder’s mindset. You move fast without confusing speed with sloppiness.

AI and Agentic Systems Experience

This is the heart of the role, and the bar is deliberately high.

You should be able to demonstrate:

• Agentic systems you have designed, built, shipped, or operated.
• Practical fluency with AI coding agents and multi-agent workflows.
• Understanding of model behavior, including context windows, retrieval failure modes, grounding gaps, hallucination patterns, calibration, prompt design, and spec design.
• Experience with structured generation, tool calls, function calling, schema-constrained output, approval workflows, and automated review.
• Experience with eval suites, regression tests, quality measurement, observability, and production monitoring for AI systems.
• Clear judgment about where AI can automate work, where human review is required, and where quality cannot be compromised.
• Systems that run when you are away from the keyboard and the instrumentation to trust them.
• Evidence that other people’s output improved because of infrastructure, tools, workflows, or platforms you built.

When you interview with us, expect to show real systems, not just talk about AI.

Nice to Have

• 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 with tool orchestration, agent memory, multi-model routing, background workers, queues, event-driven systems, workflow engines, or durable execution.
• 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.
• 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 observability tools, distributed-systems reliability, incident response, cost telemetry, or production platform operations.
• Zero-to-one, founding-engineer, or early-stage platform-building experience.

Ideal Candidate Profile

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 are architecting the systems that AI runs inside: orchestration, tools, memory, evals, review loops, observability, calibration, recovery, and human control surfaces.

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 turn unclear goals into executable specs. They turn experiments into platforms. They turn repeated manual effort into automated workflows. They turn AI demos into production infrastructure.

They have a high bar, a practical bias, and something to prove.

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.

Benefits

Compensation

The expected base salary range for this role is CAD $175,000 to $200,000, depending on experience, technical depth, demonstrated agentic systems experience, and overall fit.

This role is also eligible for participation in the Employee Stock Option Plan.

Candidates who can show exceptional agentic systems work, including production architecture, evaluation infrastructure, systems running unattended, and meaningful leverage created for other teams, will be considered at the higher end of the range.

Benefits

• Group Retirement Savings Plan matching and participation.
• Comprehensive benefits package, including health, dental, and vision coverage.
• Health and Wellness spending account.
• 15 vacation days.
• 10 wellness days.
• A founding-level seat on the systems that will define how an AI-first game studio operates.
• Exposure to live-service games, content production, game operations, internal platform development, and autonomous engineering workflows.
• A high-ownership role with meaningful influence over how AI is adopted across the company.
• A leadership team that is all-in on practical AI adoption, not performative AI theatre.

Accessibility and Accommodation

Big Viking Games is committed to creating an inclusive and accessible environment for all candidates. We welcome applications from individuals of all abilities and will provide accommodations throughout the hiring process as needed.

If you require accommodation during the hiring process, please contact [email protected] so we can work with you to support your needs.

Application Note

When you apply, tell us about an agentic system you have built or shipped. We are especially interested in what it did, how it failed, how you measured it, how you made it more reliable, and what changed because it existed.