Research Engineer, Post-Training

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