Research Engineer, Post-Training

Start free →

Or apply yourself on the official page →

About the role

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, e

View the official posting →