Member of Technical Staff
Core
Own the end-to-end evaluation platform for generating, annotating, reviewing, and adapting model evaluations at scale for frontier models.
Role type
Senior IC ML Infrastructure Engineer (Evaluation Platform)
Builds
CLIs, APIs, GUIs, and storage layers for collaborative evaluation workflows
Domain
Generative AI, LLMs, VLMs, Agents, Robotics
Deliverable
production ML models
Required skills
Python, PyTorch, Kubernetes, large-batch GPU workloads, data pipeline design, experimental statistics, internal tooling development, technical leadership
Preferred skills
evaluation suites for generative models, LLM/VLM-as-judge pipelines, online experimentation platforms, agents and robotics policy evaluations
Technologies
Kubernetes, PyTorch, Python
Responsibilities
Design and build tooling for model evaluation at scale; Partner with research teams to generalize evaluation capabilities; Set standards for reproducibility and metric definitions; Drive platform adoption across training and production; Contribute to ML Platform tools for model training and serving
Seniority
Senior, hands-on IC
