Research Engineer, Post-Training

Harvey
San Francisco
Workplace: HybridFull timeUSD 231,000 - 340,000 annuallyFunction: Education & TrainingSkills: ["Python","Research","Experimentation","Communication","Problem-solving"]

Help scale Harvey"s post-training loop by defining and running model training experiments, interpreting results, and collaborating with internal and external researchers to build better data, environments, graders, and training recipes for open-weight models in a legal tech setting.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
Harvey
Harvey
2 months ago

Research Engineer, Post-Training

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI
Last checked: 3 hours agoStatus: Live

Job Summary

Help scale Harvey"s post-training loop by defining and running model training experiments, interpreting results, and collaborating with internal and external researchers to build better data, environments, graders, and training recipes for open-weight models in a legal tech setting.
Location: San Francisco
Workplace: Hybrid
Employment Type: Full time
Job Function: Education & Training

Key Responsibilities

  • •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.

Pay and Benefits

Salary: USD 231,000 - 340,000 annually
Equity and Bonus:Equity

Key Requirements

  • •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.
Experience:AIMLLegal techEnterprise AI
Skills:PythonResearchExperimentationCommunicationProblem-solving
Languages:English
Tech Stack:PythonRLHFSFTDistillationGPUDistributed training

Company Brief

Harvey
Harvey builds domain-specific generative AI for legal and professional services, automating contract analysis, due diligence, compliance, and litigation workflows for law firms and corporate legal teams.
Industry: LegalTech
Company Size: Large (251 to 1,000 employees)
Revenue: USD 100M to 250M
Growth: Scaleup
Valuation: Unicorn (USD 1B+)
Funding: Series E+
Headquarters: San Francisco, United States
Founded: 2022
Glassdoor
Glassdoor: 4.1
WebsiteLinkedInGlassdoor