Senior Product Operations Manager, Evaluation at Harvey

This role is for a technical program manager or operations lead with at least four years of experience specifically in ML evaluation, benchmarking, or research workflows. You need to be comfortable using SQL or Python to interpret data and have a background in building systems for model accuracy. **What makes it worth a look...** Harvey is a high-growth legal AI startup backed by top-tier investors, offering a very competitive salary range up to $210,000. It’s a rare chance to take ownership of the evaluation infrastructure for agentic AI at an inflection point in the industry. **You might be a good fit if you...** * Have built human-in-the-loop data pipelines or managed high-stakes benchmarking frameworks. * Can translate complex legal methodologies into repeatable technical workflows. * Are comfortable working in a high-intensity, hybrid San Francisco environment. * Know how to audit model performance across different global jurisdictions and languages.