Staff/Sr. Staff Software Engineer, Product Engineering

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. We have 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 Staff or Senior Staff Software Engineer on the Product Engineering team at Harvey, you will own and lead engineering projects that span multiple Product Engineering teams and product lines. You'll work closely with our AI, Legal, and GTM teams to build secure systems that deliver value to our customers.

Product Engineering covers a lot of ground, and we're looking for engineers across multiple domains — backend, full stack, and AI. We want people who have built great products across consumer, enterprise, and everything in between, and who are excited about building the future of application layer and genAI products. You'll build both the surfaces where lawyers meet Harvey — web, mobile, and embedded experiences in Word, Outlook, and Slack — and the agentic capabilities that power them.

This role can be based in New York City or San Francisco, with a hybrid schedule of three days a week in office.

What You'll Do

Bring AI to where our customers already work: build Harvey across every surface — web, desktop, mobile, and embedded experiences (Google Docs, MS Word, Outlook, and Slack), and API.

Lead large, high-priority projects that span multiple teams, and define the technical bets we make over the next several quarters.

Find the problems that are business critical, prioritize ruthlessly, and make the big tradeoff calls without slowing anyone down.

Build AI-platform and AI-native capabilities — the agent harness, agent building (custom agents and workflows), tool calling, retrieval, memory and context management, personalization and tone, the thread experience, and the evals that turn model quality into product quality.

Ship the systems that make Harvey work: retrieval over petabyte-scale document corpora, ingestion growing 10x every six months, data collection across 50+ jurisdictions, and government-level security for the world's most sensitive matters.

Ship across the stack — React and TypeScript alongside Python and Postgres — architecting intuitive UX and robust APIs for streaming results, long-running processes, and complex tool-calling workflows.

Mentor senior and staff engineers, and raise the bar for how the whole org builds.

What You Have

10+ YoE (post-BS/MS) in a product-focused software engineering role, operating at Staff level or above.

Depth in full stack, backend, or agents/AI — and enough range to be useful outside it.

Experience building scalable, extensible systems that support multiple product lines.

Track record of shipping highly intuitive products in fast-growing SaaS, strong attention to detail.

Experience with React, TypeScript, CSS (we use TailwindCSS), Python, or related. For agents/AI, proficiency in Python plus hands-on work building and shipping agentic systems — agent harnesses/loops, tool use, memory, and evals — not just calling LLM APIs.

You embrace AI in how you build: AI coding tools (Claude Code, Cursor, Codex, or similar) are a core part of how you ship, and you have sharp instincts for where they accelerate work and where they fall short.