AI Engineer

Role overview

An AI platform engineering role focused on hardening reusable infrastructure that underpins LLM-based products in the healthcare benefits space. The work centers on long-running agents, context management across sandboxed execution environments, model routing for cost efficiency, and shared patterns that let product teams ship AI features faster. This is protected platform work serving real production use cases rather than a ticket queue.

Responsibilities

- Harden first-version capabilities (context management, agent state, sandboxed execution, model routing) into reusable platform patterns that other AI teams can adopt - Design state management and deployment patterns so in-flight agent tasks survive deploys, restarts, and retries and can be resumed, inspected, and replayed - Build one thoughtful mechanism for packaging context into zero-trust execution environments across platforms and retrieving refreshed context on demand - Route the right model to each job, orchestrate subagents so expensive models do only expensive work, and make token usage measurable and optimized as volume grows - Measurably reduce unplanned platform work interrupting AI product engineers so their sprints go to features rather than plumbing - Document, test, trace, and evaluate shared patterns so new engineers can adopt them in days and regressions are caught before users notice

Requirements

- Hands-on ownership of infrastructure under an LLM-based product, such as an agent runtime, context or state management, orchestration, or evaluation and tracing - Production experience shipping LLM features and living with imperfect model behavior, latency, cost, and the tradeoffs between them - Modern full-stack development in TypeScript and/or Python, integrating foundation-model APIs, tool calling, and human review into applications - Practical evaluation and tracing habits, with curiosity about what the model did and why - Ability to explain decisions to product, design, and domain experts and turn their problems into reusable capabilities

Nice to have

- Daily stack includes React, Node, TypeScript, Python, Postgres, and AWS, with multiple foundation-model providers, sandboxed execution environments, and Langfuse for tracing - Comfort using coding agents as part of daily work - Small, senior team with a direct line to leaders making product and platform decisions - Remote-first culture with a mission tied to fixing healthcare