Senior Product Operations Manager, Evaluation

What You'll Do

• Build and scale the systems that power model and product evaluations across Harvey
• Run intake, triage, and prioritization for the evaluation request queue, routing capacity to the highest-value coverage gaps
• Embed evaluation workflows and readiness checkpoints into the product development lifecycle
• Create the single source of truth for evaluation status, results, history, and launch readiness
• Turn Expert-designed evaluation methodologies into scalable, repeatable operational processes
• Manage human data providers and stand up our internal contract-attorney pipeline, ensuring evaluation quality meets legal standards
• Work with Engineering and Research to improve evaluation tooling, automation, and dashboards
• Drive evaluation readiness for major product and model launches across geographies and jurisdictions
• Document and operationalize evaluation governance as complexity increases
• Help define how Harvey ensures model accuracy, reliability, and trust at global scale

What You Have

• 4–7+ years in technical program management, product operations, research operations, or evaluation/benchmarking roles
• Experience working with ML/AI evaluations, benchmarking frameworks, or scientific workflows
• Comfort with statistical methodologies and SQL or Python, or similar tools to interpret evaluation data (either natively or with AI tool support)
• Strong business acumen with an ability to apply an ROI-focused mindset to scaling
• Ability to work deeply with legal experts and operationalize complex evaluation methodologies
• Strong cross-functional coordination skills across Product, Engineering, Research, and data providers/vendors
• High attention to detail and a bias toward clarity, rigor, and reproducibility
• Ability to navigate an evolving landscape and bring order to complex systems
• Strong communication skills and comfort translating technical nuance for diverse stakeholders
• Desire to do whatever it takes to make evaluation systems successful—from writing documentation to diagnosing pipeline issues