About the Role
We're looking for an AI Engineer to expand the AI capabilities at the core of COMO. AI sits at the heart of everything we build, and it already runs in production with our customers. You'll join a strong team building at real scale, take on meaningful ownership, and see your work make an impact on customers within weeks.
What You'll Do
Build and own our agents platform: a common runtime with typed outputs, reproducibility, evals and guardrails, cost and latency budgets, and a full audit trail
Design and ship production agents: classification, prioritization, and enrichment of what we know about each customer environment
Own agent quality as a number: offline and online evals that catch regressions before customers do
Take agents into real customer environments and use what you learn to set the roadmap
Work directly with the founders and the engineers behind our data pipelines
What We're Looking For
5+ years of experience in a Software Engineering role, including 2+ years as an AI Engineer building LLM-based systems and agents in production
Hands-on experience designing and shipping agents (tool use, orchestration, structured outputs) with real users, not demos
Experience with eval-driven development: offline and online evals, measuring quality regressions, and numbers to show for it
Strong backend fundamentals in any major language (ours is Python)
Hands-on experience with LLM APIs (Bedrock, OpenAI, or Anthropic) in production, including cost and latency budgeting
Security, infrastructure, or observability background - advantage
Early-stage startup experience - advantage