About the role
Monte Carlo is seeking a senior researcher-engineer to own end-to-end work on agent observability, from research to production. You’ll tackle ambiguous problems, prototype solutions, and integrate them with the platform alongside engineering and data science teams.
You’ll design eval infrastructure, retrieval pipelines, and guardrails for safe, scalable deployment. This remote-first role supports a global team and enterprise AI reliability initiatives.
Take an open problem end-to-end—from research and prototyping through production. Design and ship agent-powered features and integrate them into the platform. Build evaluation infrastructure: golden datasets, regression suites, scoring. Own retrieval and context pipelines over metadata, lineage, and query history. Collaborate with data science on detection quality and experiment design. Set technical bar for building with LLMs and guardrails. Experience building agents in production with autonomy. Strong Python and backend development skills. Knowledge of evaluation frameworks and datasets. Ability to work from ambiguous problems through production. Familiarity with LLMs and AI tooling.Skills
Interested in this role?
You'll apply directly on Monte Carlo's careers site.