---
title: 'Research Engineer, Post-Training at Harvey'
canonical: 'https://feeny.ai/job/research-engineer-post-training-harvey-san-francisco-qtxzwdmxt9np'
type: 'job'
last_seen: '2026-09-07'
---

# Research Engineer, Post-Training at Harvey

- **Company:** [Harvey](https://feeny.ai/companies/harvey)
- **Location:** San Francisco, CA
- **Compensation:** $231k–$340k
- **Employment:** full-time
- **Work type:** hybrid
- **Posted:** 2026-06-26
- **Last confirmed live:** 2026-09-07
- **Apply:** https://jobs.ashbyhq.com/harvey/d78083d9-a203-4ae4-b4b9-454d65df3702/application

**Skills:** Python, Post-training, Model training, SFT, Preference optimization, RLHF, RLAIF, Reward modeling, Distillation, Open-weight models, Research engineering, Distributed training, Inference systems, GPU workloads, Large-scale ML experimentation, Dataset curation pipelines, Model-output processing, Experiment tracking, Evaluation dashboards, Regression analysis tooling

> The Research Engineer will drive post-training experiments to improve agent performance in legal work, optimizing harnesses and grading systems. This role involves self-managing applied research projects, interpreting model traces, and collaborating with internal and external partners to build better data and traini...

## Job description

## 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

Post-training is how Harvey turns expert feedback and agent traces into models that are meaningfully better at legal work. We are looking for a research engineer who can help scale that loop: defining and running model training experiments, interpreting results, and working with internal and external research partners to build better data, environments, graders, and training recipes.

This role is for someone who can self-manage model training and applied research projects. You will work closely with internal and external research collaborators on post-training efforts that matter to our product roadmap. The ideal candidate has extensive hands-on experience training open weight models, either in a research or production setting, and enough engineering depth to run and debug experiments efficiently.

## WHAT YOU'LL DO

- Drive post-training experiments, pushing agent performance while navigating the Pareto frontier of cost, latency, security, and governance.
- Optimize agent harnesses, including domain-specific skills, tools, subagents, retrieval strategies, and validation loops that improve quality on long-horizon legal work.
- Design and develop grading and reward systems that are reliable enough for evaluation, efficient enough for iteration, and strict enough for high-stakes legal work.
- Study agent behavior, identifying patterns that correlate with successful work product, and converting those findings into training data, evals, or harness changes.
- Work with Harvey researchers and external research partners to define experiments, evaluate methodology, review results, and keep projects moving toward concrete model improvements.

## WHAT YOU HAVE

- Hands-on experience with post-training or model-training work, such as SFT, preference optimization, RLHF/RLAIF, reward modeling, distillation, or adapting open-weight models to specialized domains.
- Strong judgment about model behavior: you can read traces, inspect outputs, identify failure modes, and reason about whether a metric is measuring the thing that matters.
- Strong Python and research-engineering ability. You can write clean code, debug experiments, and build the simple but reliable systems needed to make research move faster.
- Ability to self-manage ambiguous applied research projects and communicate clearly with researchers, engineers, product teams, domain experts, and external partners.

## Nice to Have

- Experience building data or evaluation infrastructure for ML workflows, such as dataset curation pipelines, model-output processing, experiment tracking, evaluation dashboards, or regression analysis tooling.
- Experience with distributed training, inference systems, GPU workloads, or large-scale ML experimentation.
- Research publications, open-source contributions, or shipped industry work in LLMs, agents, evaluation, or ML systems.

## COMPENSATION

$231,000 - $340,000

DEPENDING ON YOUR LOCATION, AN APPLICANT PRIVACY NOTICE MAY APPLY TO YOU. YOU CAN FIND ALL OF OUR APPLICANT PRIVACY NOTICES [HERE https://www.notion.so/harveyai/Harvey-Candidate-Privacy-Policies-319ac3fcdd7a803bb807d5094f249922].

## #LI-AK1

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

## About Harvey

## Company Overview
- **One-liner**: Harvey builds domain-specific AI software for legal and professional services, enabling law firms and in-house teams to automate research, contract analysis, due diligence, and complex workflows.
- **Entity Type**: Private (backed by leading venture capital firms)
- **Headquarters**: San Francisco, California, United States
- **Founded**: 2022
- **Founders**: Winston Weinberg (CEO), Gabriel Pereyra (President)

## Core Business
- **Primary industry**: AI software for legal and professional services (LegalTech)
- **Target customers**: B2B – large law firms (AmLaw 100), in-house legal teams at Fortune 500 enterprises, mid-sized firms, and professional service networks across 60+ countries.
- **Mission or purpose statement**: To enable legal and professional services teams to focus on high-value work by providing a secure, expert AI platform that handles research, drafting, and complex workflows.

## Products & Services
- **Harvey Assistant**: Ask questions, analyze documents, and draft faster with domain-specific AI (SaaS).
- **Harvey Vault**: Securely store, organize, and bulk-analyze legal documents (SaaS).
- **Harvey Knowledge**: Research complex legal, regulatory, and tax questions across domains (SaaS).
- **Harvey Agents**: Purpose-built agents that execute complex legal work end-to-end (SaaS).
- **Harvey Contract Intelligence**: Surface insights, strengthen negotiations, and accelerate reviews (SaaS).
- **Harvey Command Center**: Analytics, benchmarking, and agentic insights for leading AI transformation (SaaS).
- **Harvey Mobile**: Mobile access to stay productive from anywhere (SaaS).
- **Harvey Shared Spaces**: Collaborate with legal teams across organizations in secure shared workspaces (SaaS).
- **Harvey Ecosystem**: Integration with existing tools to ground answers in trusted sources (API/platform).

## Market Standing
- **Valuation/Market Cap**: Not publicly disclosed (company is private).
- **Key Metric**: Annual Recurring Revenue (ARR) – reported in press but exact figure not disclosed; strong growth implied by 1,500+ customers and rapid hiring.
- **Notable Investors/Partners**: Sequoia, Kleiner Perkins, GV (Google Ventures), OpenAI Startup Fund, Coatue, Andreessen Horowitz, EQT.
- **Growth Signals**: 
  - Named Time100 Most Influential Companies (2025).
  - LinkedIn Top 50 Startup of 2025.
  - CNBC Disruptor 50 List.
  - 1,500+ customers across 60+ countries, including AmLaw 100 firms.
  - Headcount: ~300 employees (as of mid-2025), with aggressive hiring (254 active job postings).
  - Office expansion: San Francisco, New York City, London.

## Competitive Advantages
- **Domain specialization**: AI models trained specifically for legal and professional services, not generic LLMs.
- **Enterprise security**: SOC 2 Type II, ISO 27001/27701/42001, GDPR, CCPA compliance – meeting law firm security requirements.
- **Deep investor backing**: World-class VC network provides strategic guidance and access.
- **Strong product‑market fit**: Rapid adoption by top-tier law firms and in-house teams, with high switching costs due to embedded workflows.
- **First‑mover in agentic legal AI**: Purpose‑built agents execute end‑to‑end tasks, differentiating from simple document Q&A tools.

## Strategic Focus
- **Customization, collaboration, and simplicity**: Helping teams embed expertise into Harvey, collaborate across firms, and reduce complexity via agentic workflows.
- **Expansion beyond legal**: Long‑term ambition to transform professional services broadly (consulting, accounting, etc.).
- **Product innovation**: Continued investment in agentic AI, mobile access, and ecosystem integrations.
- **Global growth**: Scaling sales and engineering teams in existing hubs and expanding into new markets.

## Why Work Here
- **Culture**: Fast‑paced, collaborative, ambitious. Values include **Decisiveness** (“take the square root of the weather” – avoid overanalysis), **Simplicity**, and **Job’s Not Finished** (continuous improvement).
- **Work environment**: Hybrid – 3+ days per week in office for roles based in San Francisco, New York City, or London. Some fully remote positions available (clearly marked).
- **Benefits**: Comprehensive health/dental/vision insurance, 401(k) match, paid parental leave (immediately eligible), annual professional development stipend, in‑office daily lunch, and more.
- **Growth opportunities**: Rapidly scaling (~300 employees, 254 open roles) provides internal mobility and ownership of impactful projects.
- **Engineering culture**: Strong blend of AI research (DeepMind background) and legal domain expertise. CTO Siva Gurumurthy recently joined. Emphasis on building secure, enterprise‑grade products.

## Sources
1. [harvey.ai](https://www.harvey.ai/)
2. [harvey.ai/company](https://www.harvey.ai/company)
3. [harvey.ai/blog/landing-a-job-at-harvey](https://www.harvey.ai/blog/landing-a-job-at-harvey)
4. [linkedin.com/company/harvey-ai](https://www.linkedin.com/company/harvey-ai)
5. [jobs.ashbyhq.com/harvey](https://jobs.ashbyhq.com/harvey)

## Other roles at Harvey

- [Staff Software Engineer, Model Infrastructure](https://feeny.ai/job/staff-software-engineer-model-infrastructure-harvey-san-francisco-8a16y83nftsj) — San Francisco, CA
- [Senior Software Engineer, Model Infrastructure](https://feeny.ai/job/senior-software-engineer-model-infrastructure-harvey-san-francisco-6tywmebr0r9h) — San Francisco, CA
- [Head of Mid-Market Sales](https://feeny.ai/job/head-of-mid-market-sales-harvey-london-n918xg1r4jgb) — London, United Kingdom
- [Customer Experience Manager, US](https://feeny.ai/job/customer-experience-manager-us-harvey-san-francisco-2dw5w8905rz6) — San Francisco, CA
- [Transformation Associate](https://feeny.ai/job/transformation-associate-harvey-san-francisco-qm17099y4cjc) — San Francisco, CA
- [Transformation Associate](https://feeny.ai/job/transformation-associate-harvey-chicago-h0b3a2pdz2zp) — Chicago, IL
- [Transformation Associate](https://feeny.ai/job/transformation-associate-harvey-dallas-a2hzwnh0vb51) — Dallas, TX
- [Transformation Associate](https://feeny.ai/job/transformation-associate-harvey-remote-cezdb49eyhv5)
- [Transformation Associate](https://feeny.ai/job/transformation-associate-harvey-new-york-78kzq8sv2gvp) — New York, NY
- [Content Marketing Manager](https://feeny.ai/job/content-marketing-manager-harvey-san-francisco-zsjew4mcankn) — San Francisco, CA