
Software Engineer, Agents
Harvey · New York, United States
- On site
- Full-time
- $200,000 / year
- New York, United States
Email the hiring manager to get a response.
Get their verified email + an intro that's ready to send.
Subject: Interested in the Software Engineer, Agents role at Harvey
Hi Riley — I came across the Software Engineer, Agents opening and wanted to reach out directly. I've spent the last few years doing exactly this kind of work, and Harvey stood out because…
✎ Personalized to your résumé after sign-up.
- ✓ Verified email of the hiring manager
- ✓ Intro email personalized to your résumé
- ✓ $9/mo = unlimited — any job link
Secure checkout · cancel anytime
Job highlights
- Build AI systems for legal professionals.
- Design agent environments and actions.
- Optimize agent performance and execution.
- Collaborate with customers and PMs.
- Experience with Python and LLMs required.
About the role
Why Harvey
At Harvey, we’re transforming how legal and professional services operate. 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 1500+ 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 moves fast, takes ownership, and is deeply committed to the mission — operating with intensity, staying close to our customers, and pushing each other for excellence. We live by three values: Decisiveness, Simplicity, and Job's Not Finished. We act quickly on clear judgment over perfect 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.
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.
- 2-5 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.
Key skills/competency
- Agentic AI
- Software Engineering
- Python
- LLM APIs
- Agent Frameworks
- Prompt Engineering
- Model Selection
- Tool Design
- Evaluation Development
- Product Development
Skills & topics
- Software Engineer
- AI Agents
- Python
- LLM
- Legal Tech
- Agent Frameworks
- Prompt Engineering
- Model Selection
- Product Development
- System Design
How to get hired
- Tailor your resume: Highlight Python, LLM API, and agent framework experience. Quantify achievements in shipping user-facing products.
- Showcase your iterative mindset: Emphasize experience with proof of concepts, rapid decision-making, and shipping v0 products.
- Demonstrate evaluation skills: Provide examples of using evaluations to drive quality and customer delight in agent development.
- Prepare for technical questions: Be ready to discuss agent design, prompt engineering, model selection, and low-latency execution.
- Research Harvey's values: Align your application and interview responses with Decisiveness, Simplicity, and 'Job's Not Finished'.
Technical preparation
Behavioral questions
Frequently asked questions
- What specific legal workflows will a Software Engineer, Agents at Harvey work with?
- A Software Engineer, Agents at Harvey will partner with customers and PMs to understand various legal workflows. This includes automating information requests and diligence checks in M&A deals, improving the application of legal playbooks to contracts, optimizing retrieval agents for litigation cases, and tuning libraries for coding agents to enable board-ready PowerPoint generation. The focus is on practical applications that streamline critical knowledge work in the legal domain.
- What is the expected experience level for a Software Engineer, Agents at Harvey?
- Harvey is hiring for this role across Mid, Senior, and Staff levels. The typical requirement is 2-5 years of post-BS/MS software engineering experience. Candidates should also demonstrate proficiency in Python, experience with LLM APIs and agent frameworks, and a track record of shipping user-facing products.
- How does Harvey approach iteration and shipping products as a Software Engineer, Agents?
- Harvey values an iterative mindset. Software Engineers, Agents are expected to develop proof of concepts, make decisions quickly, and ship minimum viable products (v0s). The company emphasizes using practical evaluations to drive quality and customer delight, encouraging a hands-on approach to product development and continuous improvement.
- What role do evaluations play in the Software Engineer, Agents role at Harvey?
- Evaluations are crucial for driving quality and customer delight in the Software Engineer, Agents role at Harvey. Candidates are expected to be comfortable with when and how to use evaluations to improve agent performance, iterate on capabilities, and ensure the agents are indispensable to legal professionals. This includes designing practical evaluations that capture what 'excellent' means in specific legal contexts.
- What are the core values at Harvey that a Software Engineer, Agents should embody?
- The core values at Harvey are Decisiveness, Simplicity, and 'Job's Not Finished'. A Software Engineer, Agents should embody these by acting quickly on clear judgment, believing simplicity is what scales, and never being satisfied with the current state, constantly pushing for excellence and innovation.
- How important is prompt engineering and model selection for this role?
- Prompt engineering and model selection are very important for the Software Engineer, Agents role. These are key methods used to optimize agent performance. Candidates will be responsible for making model selection decisions, and optimizing agent performance through techniques like prompt engineering, tool design, and skill writing to ensure high-quality task completion.
Similar roles
Open positions we recommend based on this role.
