Senior Software Engineer

Marvin Behavioral Health•Los Angeles, CA

21h•Hybrid

About The Position

Marvin is hiring a senior full-stack engineer to build and maintain its production healthcare application, using a modern TypeScript/Next.js stack and AI in both product development and engineering workflows. This is a product engineering role, not a machine learning research position; it does not involve training models or tuning GPUs. The engineer will own features end to end across the application, backend, and AWS infrastructure, and help extend Marvin’s AI coach and develop additional LLM-powered member experiences. The role includes designing evaluation and observability for AI features, improving AI-assisted development practices, and handling sensitive health information responsibly. Engineers are expected to review all code—including AI-generated code—carefully, contribute to testing and reliability, and mentor teammates. The position is hybrid, with two days per week in the office in Los Angeles or Denver.

Requirements

At least 5 years building production web applications.
Deep experience with TypeScript, React, and Node.
Comfort across the stack, including relational data modeling, authentication flows, caching, background jobs, and cloud deployment.
A strong testing habit across unit, component, and end-to-end testing.
Strong product judgment and ability to work directly with design, clinical, and partner-facing teammates.
Daily, expert use of agentic coding tools such as Claude Code, Cursor, or Codex, including directing multi-step work and critically reviewing outputs.
Hands-on experience shipping LLM features, including prompt design and versioning, structured outputs, tool/function calling, streaming UIs, retrieval-augmented generation, and multi-turn conversation state.
Experience running evaluations and tracing production LLM traffic, and ability to explain the effects of a model-version change.
Understanding of the cost, latency, and quality trade-offs involved in LLM products, including model selection, caching, prompt compression, and fallback strategies.
Ability to recognize when an LLM is unsuitable, constrain it when appropriate, and prevent hallucinations from reaching members.

Nice To Haves

Healthcare, benefits, or other regulated-data experience, including HIPAA or SOC 2.
Experience building MCP servers or internal agent tooling for a team.
Experience with Clerk, Stripe, or Sentry.
Contributions to AI developer tooling, whether open source or internal.
Experience with Next.js.

Responsibilities

Own features end to end across the Next.js/React/TypeScript application, Prisma/Postgres backend, and AWS infrastructure.
Extend the AI coach and build LLM-powered member experiences, including retrieval over benefits data, structured extraction, guided flows, and agentic tool use against company APIs.
Design evaluation and observability for AI features to identify quality regressions as well as system failures.
Advance AI-assisted development practices through agent instructions, reusable skills, hooks, MCP integrations, and review practices.
Handle sensitive health data responsibly, including PHI boundaries, redaction, audit trails, and vendor data agreements.
Review code written by humans and AI agents critically.
Mentor teammates and raise standards for testing and reliability.