Skip to content
NEXTMOVEFDE careers · United States
Harvey

Staff Software Engineer, Agents

AI summary of the role

Build the agentic systems that make AI indispensable to legal professionals at a fast-growing legal AI platform.

What you’ll do

  • Partner with customers and PMs to understand legal workflows and design practical evaluations that capture what 'excellent' means.
  • Optimize agent performance through prompt engineering, model selection, tool design, skill writing, context window management, and eval harness development.
  • Work with model infra team to design infrastructure for low-latency agent execution, including caching strategies, parallel tool calls, or subagent patterns.
  • Improve observability and instrumentation to profile agent behavior, identify bottlenecks, and drive optimization decisions.

What you’ll bring

  • 8+ years (post-BS/MS) of software engineering experience.
  • Proficiency in Python and experience working with LLM APIs and agent frameworks.
  • Experience with shipping user-facing products, either on the backend or full-stack.
  • Passion for building effective domain-specific agents.

Technologies

Python · LLM APIs · agent frameworks · prompt engineering · eval harness · caching strategies · observability · instrumentation

About Harvey

Agentic AI platform purpose-built for elite law firms and in-house legal teams to automate research, drafting, document review, and complex matter workflows.

Private Late

Source and classification

Production engineering · Evidence for this classification:

information, we believe simplicity is what scales, and we're never satisfied with where we are. If you want to do the best work of your career alongside people who share that drive, we'd love to build with you. At Harvey, the future of professional services is being written today — and we’re just getting started. Role Overview As a Software Engineer, Agents, you'll build the systems that make our AI agents indispensable to legal professionals. You will design environments and actions for agentic professional work, make model selection decisions, manage context windows, create optimal tools, and develop evals that enable faster iteration loops to unlock new capabilities. We're looking for engineers and researchers who are immersed in the space, driven to ship impactful products, and are experienced in using practical evaluations to drive task completion quality and customer delight.
How jobs are selected

Employer postings · Data from · Sources