Harvey AI logo

Mid/Senior/Staff Software Engineer, Agents

Harvey AI

New York City, USonsite$165k-$312k/yrPosted Apr 8, 2026

At a glance

Highlights

  • World-class investor support
  • Strong product-market fit
  • Opportunity for growth
  • Impactful AI agent research

Why this role might suit you

The role allows engineers to shape cutting‑edge agentic AI for legal services, work on high‑impact products used by thousands of customers, and grow within a fast‑moving, well‑funded startup backed by top investors.

Skills

pythonllm-apiagent-frameworksevaluationmodel-selectionprompt-engineeringtool-designcontext-windoweval-harnessobservabilityinstrumentationcachingparallel-tool-callssubagent-patternsretrievalfile-editing

About the role

Why HarveyAt Harvey, we’re transforming how legal and professional services operate — not incrementally, but end-to-end. By combining frontier agentic AI, an enterprise-grade platform, and deep domain expertise, we’re reshaping how critical knowledge work gets done for decades to come.

This is a rare chance to help build a generational company at a true inflection point. With 1000+ customers in 60+ countries, strong product-market fit, and world-class investor support, we’re scaling fast and defining a new category in real time. The work is ambitious, the bar is high, and the opportunity for growth — personal, professional, and financial — is unmatched.

Our team is sharp, motivated, and deeply committed to the mission. We move fast, operate with intensity, and take real ownership of the problems we tackle — from early thinking to long-term outcomes. We stay close to our customers — from leadership to engineers — and work together to solve real problems with urgency and care. If you thrive in ambiguity, push for excellence, and want to help shape the future of work alongside others who raise the bar, we invite you to build with us.

At Harvey, the future of professional services is being written today — and we’re just getting started.

Role OverviewAs 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.

Representative Projects- Save weeks of effort on high pressure M&A deals by automating information requests and diligence checks across hundreds of thousands of files with retrieval and file editing agents.

- Dramatically speed up deal turnaround speed by improving the latency and quality of agents on applying a standard legal "playbook" to contracts.

- Ensure that our clients win their complex, data-hungry litigation cases by optimizing our multi-source retrieval agents.

- Enable board-ready PowerPoint generation by tuning the harness and libraries for coding agents.

What You'll Do- Partner with customers and PMs to understand legal workflows, design practical evaluations that capture what “excellent” means, and ship agents that get the job done.

- Optimize agent performance through prompt engineering, model selection, tool design, skill writing, context window management, and eval harness development.

- Work with our model infra team to design and implement infrastructure for low-latency agent execution, including caching strategies, parallel tool calls, or subagent patterns.

- Improve our observability and instrumentation to profile agent behavior, identify bottlenecks, and drive optimization decisions.

- Stay current on new developments in agentic systems and bring those learnings back to the products we build.

What You Have- Passion for building effective domain-specific agents.

- Iterative mindset: you develop proof of concepts, make decisions quickly, and ship v0s.

- Comfortable with when and how to use evaluations to drive quality.

- Humble and adaptable about code and frameworks. We expect you to drive adoption of new best practices as they develop.

- 3+ years (post-BS/MS) of software engineering experience.

- We are hiring for this role across Mid, Senior, and Staff levels.

- 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.

Compensation Range$165,000 - $312,000 USD

Depending on your location, an Applicant Privacy Notice may apply to you. You can find all of our Applicant Privacy Notices [here].

#LI-BB1

Harvey is an equal opportunity employer and does not discriminate on the basis of race, gender, sexual orientation, gender identity/expression, national origin, disability, age, genetic information, veteran status, marital status, pregnancy or related condition, or any other basis protected by law.

We are committed to providing reasonable accommodations to applicants with disabilities, and requests can be made by emailing accommodations@harvey.ai

Compensation

This Software Engineer role pays $165k-$312k/yr. Within typical range for software engineer roles in United States.

Questions about this role

  • How do I apply to this Mid/Senior/Staff Software Engineer, Agents role at Harvey AI?

    Click "Apply with AI Applyd" above. We auto-fill the application from your resume and answer screening questions in seconds. No copy and paste, no juggling tabs.

  • What's the typical salary for Software Engineer in United States?

    Compensation for Software Engineer roles in United States varies widely by seniority, employer size, and remote vs onsite arrangement. Check the salary range on this listing when published, or browse our Software Engineer hub for United States medians across recent openings.

  • How fast does AI Applyd auto-apply?

    Most applications complete in under 90 seconds. You can track the status in your dashboard and watch the screenshot proof land the moment the application submits.

  • What ATS does Harvey AI use?

    AI Applyd supports Greenhouse, Lever, Ashby, Workday, iCIMS, SmartRecruiters, LinkedIn Easy Apply, and most other ATS platforms. If we can submit through the platform, we do.

Want AI Applyd to auto-apply to roles like this?

We tailor your resume per posting, fill the forms, and track replies for you.