Member of Technical Staff ML Platform

You will build systems for generating, annotating, scoring, tracking, and reporting model evaluations. You will define reliable evaluation standards, work with research teams, develop internal tools and data systems, and support adoption across model training and production serving.

Responsibilities

• Own the model-evaluation platform end to end
• Build systems to generate, annotate, review, and adapt evaluations at scale
• Define evaluation CLIs, APIs, GUIs, and storage layers
• Gather measurement needs from research teams and generalize solutions into the platform
• Set standards for reproducibility, metrics, reporting, and decision readiness
• Support platform adoption across training and production model serving
• Contribute to ML Platform tools and systems

Requirements

• 5+ years of experience building production ML infrastructure or data platforms
• Experience with evaluation, experimentation, or benchmarking systems
• Strong Python and PyTorch skills
• Experience running batch GPU workloads on Kubernetes
• Experience with data pipelines and storage for media or model outputs
• Knowledge of versioning and reproducibility
• Knowledge of experimental statistics
• Experience building internal tools from command line to browser
• Knowledge of the model development lifecycle