Applied AI Engineer

Why Harvey

Harvey is a secure AI platform for legal and professional services that augments productivity and automates complex workflows. Harvey uses algorithms with reasoning-adept LLMs that have been customized and developed by our expert team of lawyers, engineers and research scientists. We’ve found product market fit and are scaling our team very quickly. Some reasons to join Harvey are :

Exceptional product market fit : We have partnered with the largest law firms and professional service providers in the world, including Paul Weiss , A&O Shearman , Ashurst , O'Melveny & Myers, PwC , KKR, and many others.

Strategic investors : Raised over $500 million from strategic investors including Sequoia, Google Ventures, Kleiner Perkins, and OpenAI.

World-class team : Harvey is hiring the best talent from DeepMind, Google Brain, Stripe, FAIR, Tesla Autopilot, Glean, Superhuman, Figma, and more.

Partnerships : Our engineers and researchers work directly with OpenAI to build the future of generative AI and redefine professional services.

Performance : 4x ARR in 2024.

Competitive compensation.

Role Overview

As an Applied AI Engineer on the Engineering team at Harvey, you will own and lead engineering projects across our various product lines. We are looking for individuals who have worked across the stack on incredible products and have experience building products where machine learning models are a core component.

This role is based in San Francisco, CA. We use an in-person work model and offer relocation assistance to new employees.

What You'll Do

Conduct data collection, experimentation, and analysis to drive algorithmic development for RAG and multi-step AI pipelines.

Zero-to-one product development : rapidly prototype, evaluate, integrate, and test new product features in close partnership with our legal team.

Develop new AI native workflows : implement streaming, long-running tasks, procedural UX, etc. for new AI tasks, finding the balance between state-of-the-art and pragmatism.

Representative Projects

Partner with our legal team to design and implement a method for evaluating the correctness of document citations. Use this to build a large dataset of ground-truth citations and then improve our core citation algorithm. You can read about some of our work on evaluation and citations here ( 1 , 2 , 3 ).

Make targeted improvements to our RAG pipelines to improve answer quality for user questions over corpuses of complex data, like massive banks of spreadsheets or Japan’s tax code.

Design and build systems that leverage state-of-the-art LLMs from multiple model providers, including custom models.

Work across the stack and with our legal team to create seamless multi-step AI workflows for complex legal tasks, like corporate merger due diligence.

What You Have

3+ years of experience (post-BS / MS) in an engineering role.

Experience with shipping a scaled and impactful product powered by machine learning : how to use offline datasets, online experiments, and recent research to build simple and high performance systems. Prior experience with LLMs and retrieval pipelines is not required.

Track record of shipping reliable products and a strong attention to detail.

Experience building backend platforms that can support multiple product lines.

Grit - experience working at early-stage startups is a plus.

Please find our CA applicant privacy notice here .

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 in the early innings of a generational company. Joining early at a hypergrowth startup has proven to lead to exponential growth in responsibility, access, and ability. Apply here today!