Join Harvey as a Research Engineer/Scientist to build data and evaluation systems for legal AI applications in a fully remote role.
Posted by employer 2 days ago
First seen on Joblaze 1 day ago
Last verified on the company career page 8 hours ago
What you'll build
- Build synthetic data pipelines for training and evaluation samples
- Design evaluations and verifiers for legal work
- Build and maintain capability benchmarks
- Define quality metrics and grading mechanisms
- Close the loop from product usage to new evaluations
Must have
- Experience building data pipelines
- Strong Python skills
- Ownership of production-quality code
Nice to have
- Experience with synthetic data
- LLM evaluations
- Automated raters
- Preference data
AI in the day-to-day
You'll own synthetic data pipelines and evaluation systems that power our post-training efforts for legal AI models.
Not disclosed in this posting: years of experience, visa sponsorship.
Joblaze summary
In the role of Research Engineer / Scientist at Harvey, the individual will focus on developing data and evaluation systems that enhance the performance of AI models in legal contexts. Key skills include building synthetic data pipelines and designing evaluation metrics, with a strong emphasis on Python programming and statistical reasoning. This position is suitable for those with a background in data engineering or machine learning, particularly at various experience levels. The team operates with a high standard of excellence and is committed to continuous improvement based on customer feedback.
Joblaze insights
- Listed yesterday — first seen on Joblaze October 31, 2026. Last confirmed on Harvey's careers page November 1, 2026.
- This exact title is also open at 1 other location at Harvey: London.
- Salary band is above the typical range for AI/ML roles (median ~$190,000).
- Starts above 50% of 123 comparable staff ai/ml roles that list Python we track (median $230,000 across 42 companies). See Python salary trends
- Python appears in 44.5% of 485 comparable staff ai/ml roles; AI/ML appears in 33% of 485 comparable staff ai/ml roles.
Quick facts
- Is the Research Engineer / Scientist, Data & Evals role remote?
- Yes — Harvey lists this as a fully remote position.
- What's the salary range?
- Harvey lists $230,000–$450,000 for this role.
- What's the tech stack?
- Joblaze extracted these technologies from the posting: AI/ML, Python.
- What seniority level is this role?
- Harvey targets staff-level candidates for this position.
- Is this full-time or contract?
- Full-time for this Research Engineer / Scientist, Data & Evals role at Harvey.
From the original posting
Role Overview
As a Member of Technical Staff, Data & Evals in Harvey Research, you’ll build the data and measurement systems that power our post-training, benchmarking, and agent capability efforts.
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 synthetic data pipelines, evaluation design, the tasks and grading behind training environments, and the systems that turn feedback from domain experts into training signals and rewards. These are tasks where correctness often can’t be verified automatically, so defining and measuring quality is a core research challenge. 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 who can build reliable data and evaluation systems, question what a metric actually tells us, and work closely with researchers and legal experts to turn model failures into measurable improvements.
Learn more about our work at harvey.ai/research.
What You'll Do
Build synthetic data pipelines that generate, filter, and curate training and evaluation samples for complex legal reasoning and agentic workflows.
Design evaluations and verifiers that reflect real legal work, calibrate them against expert judgment, and investigate where they fail.
Build and maintain capability benchmarks like our Legal Agent Benchmark (LAB), along with product-focused evals that track how models perform on real customer workflows.
Work with legal domain experts to define quality metrics, rubrics, and other grading mechanisms for training and evaluation.
Own training and evaluation data quality, including provenance, coverage, and safeguards against contamination.
Close the loop from product usage and customer feedback to new evaluations and training data, so models improve where customers need them most.
Partner with researchers to investigate model failures, distinguish real gains from misleading metrics, and use findings to guide training and release decisions.
What You Have
Experience building data pipelines, ML evaluation systems, or experimentation tooling, with strong Python skills and ownership of production-quality code.
A rigorous approach to measurement, including statistical reasoning, experimental design, and understanding when a metric can mislead.
The ability to translate ambiguous goals or expert judgment into structured datasets, rubrics, and measurable criteria.
Experience with synthetic data, LLM evaluations, automated raters, or preference data is a plus. Strong data and measurement engineering experience close to ML model development is valuable even without prior LLM work.
We are hiring for this role across multiple levels.
Compensation
$230,000 - $450,000 USD
#LI-DZ1
Standard company text repeated across Harvey's postings is omitted here.