Leads the team you would join
Signs off on engineering hires
Owns the opening
From your own Gmail and LinkedIn.
About the role
This is a senior, full-time remote role for an engineer who will own AI improvements to Oyster AI, the assistant used by customers and internal team members. You will take a change from problem definition through design, evaluation, rollout and post-launch learning, with hands-on product work rather than research or prompt tuning alone. The role is open worldwide, and you will also help other product teams build AI features by sharing patterns and reviewing code. The backend is Ruby on Rails and the frontend is React, but engineers from other stacks are welcome.
What you’ll do
- Lead end-to-end improvements to Oyster AI, from defining the problem through rollout.
- Design agent tools with clear contracts, error handling and bounded execution, with human control over consequential actions.
- Choose retrieval, embedding, indexing and data freshness approaches that respect data access boundaries.
- Build evaluation loops using representative datasets, experiments, regression checks and calibrated automated judges.
- Diagnose production failures across prompts, retrieval, tools, models and infrastructure, and verify fixes with evidence.
- Document model and design choices and the criteria used to roll them out.
- Support other product teams through code review, pairing and mentoring so they can ship AI features on their own.
What they’re looking for
- A track record of independently leading complex production work from design through operation.
- Hands-on experience shipping LLM-powered product features with clear ownership of implementation decisions.
- Real depth in at least one of retrieval or RAG, evaluation datasets, LLM-as-judge, or agents and tool calling.
- The ability to separate model, retrieval, tooling and application failures and validate changes with evidence.
- Solid fundamentals in coding, debugging, testing, API integration and system design, and willingness to work in Ruby on Rails and React.
- Sound judgment on sensitive data, access control, model limits and operational risk.
- Clear written and verbal communication with product and engineering partners, and practical mentoring.
Nice to have
- Production experience with Ruby on Rails, particularly adding AI capabilities to an existing backend.
- Full-stack delivery of conversational or assistant experiences.
- Slack or in-app assistant integrations that handle user and permission context.
- Experience running retrieval pipelines, agent tools, evaluation infrastructure or model routing and cost controls at scale.
- Experience helping several teams adopt shared AI patterns.
What’s on offer
- Competitive salary with equity participation.
- Health coverage and pension or retirement provision through the employer's platform.
- Flexible hours and an async-first working culture.
- Up to 40 days off per year including holidays, or more where local law requires.
- A monthly wellbeing allowance and access to a mental health service.
- At least three months of paid parental leave for all new parents, with job protection for up to 12 months or as required locally.
- A stipend for laptop and home office equipment, plus co-working space access.
- A learning and development budget.
- Work from any country, provided the work is timely and you are authorised to work where you live.
Skills
Questions about this role
Is this role remote?
Yes. The role is fully remote and open to candidates anywhere in the world who are authorised to work where they live.
Do I need Ruby on Rails experience?
No. Rails experience is listed as a bonus, and engineers from other stacks with strong AI engineering depth are encouraged to apply.
Is a salary figure published?
The posting states a competitive salary with equity participation but does not give an amount.
How much time off is included?
The posting offers 40 days off per year including holidays and vacation, or more where local law requires.