Research Engineer, Privacy Evals — Frontier AI Safety

Meta Careers; Menlo Park (CA); On-site; USD 154,000 - 217,000; Full time

Job summary

Meta Superintelligence Labs is seeking a Research Engineer to design and maintain evaluations for frontier AI models, focusing on memorization and privacy risks to ensure safe model behavior across the lifecycle.

You will work with researchers to build scalable evaluation pipelines, generate auditable reports and model cards, and collaborate across policy, legal, and engineering teams to align with launch timelines.

Qualifications

• Bachelor's degree in Computer Science, Computer Engineering, or equivalent practical experience.
• 1+ years of experience in ML engineering, LLM research, or a related technical role.
• Background in privacy-preserving LLM development, memorization, pretraining data curation and post-training alignment.
• Proficiency in Python and experience with machine learning frameworks.

Responsibilities

• Build and refine evaluations for multimodal and agentic frontier AI models across pretraining and post-training.
• Build robust, reusable evaluation pipelines that scale across model lines and product areas.
• Produce auditable technical artifacts, including evaluation reports and model cards, with high reliability.

Skills

Python

LLM research

Privacy-preserving ML

ML engineering

Software engineering practices

Education

Bachelor's degree in Computer Science or Computer Engineering

PhD or Master's in CS or related field

Tools

Version control

Benchmarks for LLMs

Distributed systems

Job description

Meta Superintelligence Labs is seeking a Research Engineer to design and maintain evaluations for frontier AI models, focusing on memorization and privacy risks to ensure safe model behavior across the lifecycle.

You will work with researchers to build scalable evaluation pipelines, generate auditable reports and model cards, and collaborate across policy, legal, and engineering teams to align with launch timelines.