Get Started
Hunting for you, 24x7Get the iPhone app

Your hunt runs in your pocket, and tells you the moment a strong match opens.

Download on theApp Store
OysterPosted in November 2026

Senior AI Product Engineer

18 countriesSeniorRemote
Who we'd reach at OysterFound and reached by Power Apply
Best leadEngineering manager

Leads the team you would join

Technical recruiter

Owns the opening

Team member

On the team, can refer you

Power Apply

From your own Gmail and LinkedIn.

About the role

This is a senior, fully remote product engineering role for an engineer who builds LLM-powered features, open to candidates across 18 countries. The job centres on Oyster AI, the company's assistant for customers and internal team members, where you own improvements from problem definition through evaluation, rollout and production learning. Backend work is in Ruby on Rails and frontend in React, but engineers from other stacks are encouraged to apply.

What you’ll do

  • Own complex Oyster AI improvements end to end, from design and implementation through evaluation and safe rollout.
  • Design tool contracts, error handling and bounded execution for agents, with human control over consequential actions.
  • Choose retrieval, embedding, indexing and data freshness strategies 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 system trade-offs and the criteria used to roll out changes.
  • Mentor and review code for other product teams so they can deliver AI features independently.

What they’re looking for

  • Senior engineering judgment and a record of leading complex production work from design through operation.
  • Hands-on experience shipping LLM-powered product capabilities, with clear personal responsibility for delivery decisions.
  • Real depth in at least one of: retrieval or RAG, evaluation datasets, LLM-as-judge, or agents and tool calling.
  • Ability to separate model, retrieval, tooling and application failures and validate improvements with evidence.
  • Strong coding, debugging, testing, API integration and system design skills, and willingness to work in Ruby on Rails and React.
  • Sound judgment on sensitive data, access control, model limitations and operational risk.
  • Clear communication of trade-offs and effective asynchronous collaboration.

Nice to have

  • Production experience with Ruby on Rails, especially integrating AI into an established backend.
  • Full-stack delivery of conversational or assistant experiences.
  • Slack or in-app assistant integrations with clear 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

  • Fully remote, asynchronous working with no office or headquarters.
  • Work from anywhere, provided work is timely, the team is supported, and you are authorised to work where you live.
  • 40 days off per year including holidays and vacation, or more where local law requires.
  • Access to a mental health service and a monthly wellbeing allowance.
  • At least three months of paid parental leave for new parents, with job protection of up to 12 months or as required locally.
  • A stipend for laptop and home office equipment.

Skills

Questions about this role

Is this role remote?

Yes. The role is fully remote and open to candidates in 18 countries, with work-from-anywhere arrangements where authorised to work.

How much experience is needed?

The role is senior and asks for a track record of independently leading complex production work and shipping LLM-powered capabilities.

Do I need Ruby on Rails experience?

No. Rails experience is a bonus, and strong AI engineers from other stacks are welcome to apply.