Product Manager, Evals & Improvement

JobsCloseBy Editorial Insights

Meta seeks a Product Manager, Evals & Improvement for the Agent Transformation Accelerator’s Metamate platform in New York City. This early-stage, high-leverage role owns the end-to-end feedback and improvement system, defining how we measure agent quality across accuracy, helpfulness, reliability, and safety, building scalable signals, and partnering with ML and data science to translate feedback into model improvements and eval frameworks. You’ll drive the evals strategy, decide what “good” means, detect regressions, and ensure transparency across the ATA Product team with tight collaboration to engineering, data science, and Meta Superintelligence Labs. Ideal candidates have 5+ years of product management, strong quantitative skills, and a proven track record building AI evals end-to-end, including RLHF, annotation systems, and ethics considerations. To apply effectively, highlight end-to-end metric design, instrumentation, experiments that moved product metrics, collaboration with ML teams, and concrete examples of responsible AI work and staying current with AI advances.

---

The Agent Transformation Accelerator (ATA) Product team is building Meta’s future of work: Metamate, an internal full-stack platform that lets people direct, review, and help agents improve their work across the entire company. We’re building the platform components, memory systems, improvement loops, and shared product experiences that make agentic AI genuinely useful for product development. This role owns how we measure and raise the quality of agentic systems (multi-step trajectories, tool use, and partial credit).

This is an early-stage, high-leverage role that contributes directly to Metamate's topline revenue, growth, and velocity. You'll shape the approach from the ground up in a space where the right metrics don't yet exist, defining what "good" means for agents and owning the eval verdict that gates model upgrades, harness changes, and major launches. Expect to be constantly learning, working shoulder-to-shoulder with engineering, data science, and ML, including our partners across ATA and Meta Superintelligence Labs (MSL), to turn signal from real usage into a continuous improvement loop that makes the product measurably better every week.

Responsibilities
Own the end-to-end feedback and improvement system: collection, analysis, prioritization, and resolution.
* Define how we measure agent quality across dimensions (accuracy, helpfulness, reliability, safety).
* Build product mechanisms that capture implicit and explicit user signal at scale.
* Partner with ML and data science to turn feedback into model improvements, eval frameworks, and training data.
* Drive the evals and measurement strategy: what "good" looks like, how we detect regressions, and how we track progress.
* Create transparency and accountability for quality across the ATA Product team.

Qualifications
Strong quantitative skills and experience defining complex metrics
* Comfort with ambiguous problem spaces where the right metrics do not yet exist
* 5+ years of relevant industry experience with at least 2 years in Product Management
* Bachelor's degree (or relevant degree equivalent): STEM subject ideal but not essential (Computer Science, Engineering, Information Systems, Analytics, Mathematics, Physics, Applied Sciences)
* Experience partnering closely with data science and ML engineering teams
* Track record of driving product improvements through data and experimentation
* Direct experience building evals for AI products end to end: task set construction, rubric design, instrumentation, and analysis
* Experience running eval-driven development cycles, with a clear view of where evals are informative and where they mislead
* Willingness to get into the weeds of eval data and rubrics, with high standards for eval rigor and an obsession with quality
* Deep understanding of LLM capabilities and failure modes Experience building annotation, labeling, or crowd-sourcing systems
* Experience with reinforcement learning from human feedback (RLHF) or similar human-in-the-loop systems
* Background in evals, trust and safety measurement, or ML quality infrastructure
* Demonstrated ability to integrate AI tools to optimize/redesign workflows and drive measurable impact (e.g., efficiency gains, quality improvements)
* Experience adhering to and implementing responsible, ethical AI practices (e.g., risk assessment, bias mitigation, quality and accuracy reviews)
* Demonstrated ongoing AI skill development (e.g., prompt/context engineering, agent orchestration) and staying current with emerging AI technologies