Research Engineer / Scientist, Reinforcement Learning
- Posted 2 weeks ago · via Ashby
Hiring in some regions only
Full 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 In this role, you'll own how we adapt and improve leading open-weight models for legal work. We recently post-trained our first model built for legal work, and we’re now building the team to scale up our post-training efforts. You’ll own the post-training recipe across SFT and RL, including reward design and verification for challenging, semi-verifiable legal tasks. You’ll help set the research direction and carry ideas from experiments through training runs to models used by customers. You’ll join a small, high-bar team of hands-on engineers and researchers, where each person owns a large part of the work. We’re looking for research engineers and scientists who have gotten training runs working at scale, are immersed in RL for language models, and want their work to reach users quickly. Learn more about our work at harvey.ai/research http://harvey.ai/research. WHAT YOU'LL DO - Own and pursue a research agenda to improve model capability on long-horizon legal reasoning and agentic workflows. - Design and run post-training experiments across SFT and RL, building on leading open-weight models. - Develop reward functions and verifiers for semi-verifiable tasks, including rubrics, learned preference models, and expert preference data, and study where they break. - Run and debug training at scale, addressing divergence, reward hacking, and instability. - Build and use rigorous evals to track improvements and decide what ships. - Design, implement, test, and debug code across our research stack. WHAT YOU HAVE - Hands-on experience post-training LLMs with SFT and RL, including preference optimization, and direct ownership of training runs and results. - Deep ML fundamentals and experience getting distributed training runs working reliably. - Strong engineering skills in Python, with production-quality code and end-to-end system ownership. - Research experience in RL for language models or reward modeling, with the ability to move quickly from experiments to shipped improvements. Publications welcome, not required. We are hiring for this role across multiple levels. COMPENSATION $230,000 - $450,000 USD DEPENDING ON YOUR LOCATION, AN APPLICANT PRIVACY NOTICE MAY APPLY TO YOU. YOU CAN FIND ALL OF OUR APPLICANT PRIVACY NOTICES HERE https://harveyai.notion.site/Harvey-Candidate-Privacy-Notices-319ac3fcdd7a803bb807d5094f249922?pvs=74. #LI-DZ1 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
Not quite right? Similar roles hiring now
See all 4 similar →Employer hires only in specific regions — check eligibility first
Explore related
Market data & reports
Salary & skill-demand research built from our own listings data.
- Skills Remote Employers Ask For in the AI EraMost-named skills in active listings by kind, AI-named skills and the fastest risers. Weekly data.
- Indonesia IT Jobs vs Global Remote (2026)Primary analysis of 2,049 listings: methodology, classification rules, downloadable datasets.
- AI-Skill Demand: Indonesia vs Global Remote (2026)10,000+ postings, taxonomy-first classifier, Wilson CIs, pre-registered before analysis.
- Remote ≠ Remote: The Skills That Open Global Work to Indonesians (2026)12,891 remote listings: the highest-paid coding skills are the most geo-locked for Indonesia-based applicants. CC BY 4.0 aggregate dataset.
- The Compliance Layer of the AI Hiring Stack (2026)6,349 remote listings: 77.2% never state who may apply. Methodology and a CC BY 4.0 aggregate dataset.
- AI in Job Ads: Indonesia vs Global (2026)Global engineering ads naming AI rose from 3.4% to 23% after ChatGPT; Indonesian ads went from 2.2% to 2.8%. 2027 scenarios and a CC BY 4.0 dataset.
- Future of Jobs Index: every quarterly editionOne index per quarter from global remote and Indonesian job ads. Q4 2026 is the baseline (= 100); later editions are measured against it on the same sources.
- Future of Jobs Index, Q3 2026 (pre-baseline)Global remote and Indonesian job ads by job family: AI-skill demand, remote reach, pay transparency and seniority. Every figure with its sample size. CC BY 4.0 dataset.
- The Laptop Job Recession: Indonesia's Coders and Their Job Ads (2026)Indonesia's coders multiplied by eight while software job ads fell by two-thirds. 284,000 archived Southeast Asian job ads, 2019–2026, charts by job family and 2027 bets. CC BY 4.0 dataset.
- Pandora's Box Ep. 1: AI and Southeast Asian Job Ads (2026)118,545 archived job ads, 2019–2026: web and software developer ads shrank on every board, a phone app became the entry ticket, and a Job X-ray for 17 jobs. CC BY 4.0 datasets.
- Cron vs LLM vs LangGraph vs Agent for Social Posts (2026)A pre-registered test of four ways to turn a blog post into social posts, on two models. Automated checks picked a cron template; the model mattered more than the framework.
- Indonesia Hiring Report: Tech vs Non-TechJob demand by field from aggregate open-job counts — never individual listings.
- Indonesia Salary BenchmarkAggregate salary ranges across roles, with open methodology and dataset.
- Indonesian Remote Work Salary & Demand IndexHow much of the global remote job corpus is open to Indonesia, and what it pays (USD) by role.
- Indonesia Quarterly Labor Market ReportLayoffs, funding, salaries & skills per quarter — open aggregates.
- Remote Market Reports by RoleAuto-generated per role family — skills, seniority, companies, salary.
- Global Remote Salary BenchmarkAnnual salary by role & currency, plus the share of listings open worldwide.
This employer appears to hire only in certain regions.