3 months ago
Base Salary
$231k - $340k/yr
Responsibilities
- Partner with customers and product managers to understand legal workflows, define practical evaluations, and ship effective agents.
- Optimize agent performance through prompt engineering, model selection, tool design, skill writing, context-window management, and evaluation-harness development.
- Design and implement low-latency agent-execution infrastructure with model infrastructure engineers, including caching, parallel tool calls, and subagent patterns.
- Improve observability and instrumentation to profile agent behavior, identify bottlenecks, and guide optimization.
- Track developments in agentic systems and apply relevant learnings to Harvey products.
Requirements
- 5–8 years of post-BS/MS software engineering experience.
- Proficiency in Python and experience with LLM APIs and agent frameworks.
- Experience shipping user-facing products on the backend or full stack.
- Passion for building effective domain-specific agents and using evaluations to drive quality.
- Ability to develop proofs of concept, make decisions quickly, and ship early product versions.
- Adaptability with code and frameworks and willingness to drive adoption of evolving best practices.
Tech Stack
Categories
About Harvey
Harvey builds domain-specific generative AI for legal and other professional services, delivered as an enterprise platform and APIs to automate contract analysis, due diligence, compliance, and litigation workflows. Founded in 2022 and headquartered in San Francisco, it sells to law firms and corporate legal departments on enterprise agreements; investors include Sequoia Capital and OpenAI. Customers include multiple Am Law 100 firms and Fortune 500 companies’ legal teams.