← All roles

Engineering Manager, AI Platform

Harvey· Engineering
Apply on company site
San Francisco$272k - $355kFull-timePosted 5d ago

About the role

Engineering Manager responsible for leading and scaling a team building the foundational AI platform powering Harvey’s products, including model access, routing, agent orchestration, evaluation frameworks, and observability to run LLM-powered products at scale.

Responsibilities

  • Lead and grow a team of engineers building the core AI platform that powers Harvey’s products
  • Define the roadmap for shared AI infrastructure, including model gateways and routing, agent orchestration, tool calling, prompt and context management, and long-running job execution
  • Partner with Product, Research, and product engineering teams to understand their needs and turn recurring patterns into reusable, well-documented platform primitives
  • Build and scale evaluation, testing, and monitoring systems so teams can measure quality, catch regressions, and ship AI features with confidence
  • Drive reliability, latency, cost efficiency, and security across LLM-powered systems, including working with model providers on capacity, rate limits, and new capabilities
  • Evaluate and rapidly adopt new models, frameworks, and techniques, and decide what to build, buy, or adopt
  • Contribute to code and architecture reviews, unblock teams, and lead by example when needed
  • Hire, grow, and retain exceptional engineers who thrive in a high-trust, high-impact environment

Qualifications

  • 2+ years of experience in a software engineering management role leading platform, infrastructure, or full stack product engineering teams, preferably in high-growth environments
  • 5+ years of experience as a backend, infrastructure, or full stack engineer
  • A track record of leading high-performing, engaged engineering teams
  • Experience building and operating production systems powered by LLMs (for example agents, retrieval, tool use, or evaluation pipelines)
  • Experience building internal platforms or shared services that other engineering teams depend on, and partnering with cross-functional stakeholders to prioritize them
  • Strong backend engineering skills in modern languages and frameworks (e.g. Python, Go, Node) and familiarity with distributed systems concepts
  • Sound judgment on tradeoffs among quality, latency, cost, and speed of delivery in AI systems
  • A plus: Experience with durable job execution frameworks, MCP or other tool and context protocols, LLM observability and eval tooling, or working directly with model providers

Skills

Required:Leadership of engineering teamsBackend engineeringLLM-powered systems

Benefits

  • Comprehensive health, dental and vision coverage
  • retirement benefits (401k match up to 4%)
  • flexible PTO
  • equity plan and benefits program eligibility
Last updated Oct 22, 2026. Interested? Apply on the company site.
Harvey logo

About Harvey

Professional Class AI

Harvey is a platform built to meet the standards of the world’s leading professional service firms.

AILegalLegal AILegal AnalysisLegal Document AnalysisLegal ResearchLegal Techsetter-30
Company profileWebsite

More open roles at Harvey