Senior AI Product Engineer

✨ One platform, a whole world of opportunity The best jobs have always clustered in a handful of the world's wealthiest cities. But talent is everywhere. Oyster set out to close that gap - building a global employment platform that lets companies hire, pay, and care for brilliant people anywhere. We're proof that a high-performing culture doesn't need an office. Distributed across 60+ countries since 2020, we've built something the industry keeps noticing: Ranked #10 of 250 on TIME and Statista's 2026 list of America's Top WorkTech Companies Named one of America's Greatest Startup Workplaces 2026 by Newsweek A G2 Spring 2026 Leader across Employer of Record, Global Employment, Multi-country Payroll, and HR Compliance The only B Corp-certified global employment platform ~ independently verified since 2023 Two of those rankings measured our business impact from the outside. One measured how our own people feel about working here. They landed in the same place ~ because at Oyster, culture and performance aren't separate conversations. They're the same one. And we're just getting started. If you want to do the best work of your career alongside people who care as much as you do, we'd love for you to apply. The Opportunity Oyster AI is our assistant for customers and team members, and we want it to be genuinely useful: accurate, fast, reliable and safe with the data it touches. In this role you’ll own complex improvements to it end to end, from defining the problem and designing the solution through evaluation, rollout and learning from production. Your work will span agent capabilities and tools, knowledge retrieval, answer quality and infrastructure, with real trade-offs between model quality, latency, reliability and cost. This is a hands-on product engineering role, not a research-only or prompt-only position. You’ll also help other product teams build AI features well by sharing patterns, pairing with them and improving the reusable foundations they rely on. Our backend is Ruby on Rails and our frontend is React. Strong AI engineers from other stacks are very welcome, and Rails experience is a bonus, not a prerequisite. What You’ll Build & Own End-to-end AI improvements. Connect user needs to architecture, implementation, evaluation and safe rollout for complex Oyster AI work. Reliable agents and tools. Design clear tool contracts, robust error handling and bounded execution, with appropriate human control over consequential actions. Better knowledge access. Choose retrieval, embedding, indexing and freshness strategies that improve answers while respecting data access boundaries throughout retrieval and generation. Evaluation you can trust. Build evaluation loops with representative datasets, experiments, regression checks and, where useful, automated judges calibrated against human judgment. Root-cause fixes in production. Diagnose failures across prompts, retrieval, tools, models and infrastructure, fix the underlying cause and verify the fix with evidence. Explicit trade-offs. Choose models and system designs deliberately, and document decisions and rollout criteria. AI capability across teams. Support other product teams through technical guidance, code review, pairing and mentoring, so they can deliver AI features independently. What You’ll Bring Senior-level engineering judgment and a track record of independently leading complex production work from design through operation and improvement. Hands-on experience shipping LLM-powered product capabilities to production, with clear personal responsibility for implementation and delivery decisions. Real depth in at least some of the following: retrieval/RAG and indexing, evaluation datasets and experiments, LLM-as-judge, or agents and tool calling. The ability to tell model, retrieval, tooling and application failures apart, and to validate improvements with evidence. Strong fundamentals in coding, debugging, testing, API integration and system design, plus willingness to work in Ruby/Rails and React. Sound judgment about sensitive data, access control, model limitations and operational risk. Clear communication of trade-offs, effective async collaboration with product and engineering partners, and practical mentoring. Nice to have Production experience with Ruby on Rails, especially integrating AI capabilities into an established backend. Full-stack delivery of conversational or assistant experiences. Slack or in-app assistant integrations with clear user and permission context. Operating retrieval pipelines, agent tools, evaluation infrastructure, or model routing and cost controls at production scale. Helping multiple teams adopt reusable AI patterns while balancing shared foundations against local needs. Why Join Us Real AI in production. You’ll ship to real users, and success is measured by evaluations and user outcomes, not plausible-looking demos. Ownership of hard problems. You’ll work across agents, retrieval, evaluation and infrastructure, w