Senior Safety Evaluation Engineer (ML Metrics)

Meta; Menlo Park (CA); On-site; USD 219,000 - 301,000; Full time

Job summary

Meta is seeking a Research Engineer to advance Safety Evaluation for its frontier AI systems. You will set the strategy across model families and modalities, design novel safety evaluations, and build a distributed platform to run extensive checks against training checkpoints and production traffic.

You will translate policy and regulatory standards into concrete measurement criteria while mentoring researchers and communicating results to leadership.

Qualifications

• Experience designing and validating evaluations or benchmarks for ML systems, including metric reliability and failure modes.
• Hands-on work with LLMs, multimodal models, or NLP across production or research environments.
• Ability to communicate technical results to non-technical stakeholders and drive decisions across teams.

Responsibilities

• Set the technical strategy for safety evaluation across multiple model families and modalities.
• Design, implement, and validate novel evaluations for safety-critical behaviors (policy adherence, adversarial robustness, agentic risk).
• Build and harden distributed evaluation platforms to run hundreds of evals at scale during training.

Skills

Python

PyTorch

ML/AI

LLMs

Education

Bachelor's degree in CS/Engineering or equivalent

Tools

PyTorch

Job description

Meta is seeking a Research Engineer to advance Safety Evaluation for its frontier AI systems. You will set the strategy across model families and modalities, design novel safety evaluations, and build a distributed platform to run extensive checks against training checkpoints and production traffic.

You will translate policy and regulatory standards into concrete measurement criteria while mentoring researchers and communicating results to leadership.