Lead AI Safety Evaluation Engineer

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

Benefits offered by this job

Bonus

Equity

Benefits

Job summary

Meta in Menlo Park is seeking a Research Engineer for the Safety Evaluation team within Meta Superintelligence Labs. You will design evaluations that measure safety across text, image, voice, video, and agentic systems, and build the infrastructure to run them continuously through training checkpoints and production traffic.

Join a team shaping measurement standards that gate launches and influence roadmaps across the AI portfolio, mentoring engineers and partnering with Policy, Legal, and

Qualifications

• Bachelor's degree in Computer Science, Computer Engineering, a relevant technical field, or equivalent practical experience.
• 3+ years of industry research or research-engineering experience in ML/AI, including hands-on work with LLMs, multimodal models, or NLP.
• Experience setting technical direction across multiple teams and evaluating ML systems.

Responsibilities

• Set the technical strategy for safety evaluation across model families and modalities and drive it to execution.
• Design, implement, and validate novel evaluations for safety-critical behaviors and for capabilities with no established benchmark.
• Build and harden a distributed evaluation platform that runs hundreds of evals at scale during training.
• Own measurement quality: signal/noise, power, saturation, contamination, and construct validity for gating launches.
• Create, curate, and analyze high-quality safety datasets and translate red-team findings into durable signals.
• Diagnose anomalous eval results and communicate clear answers under time pressure.
• Own dashboards and reporting used by researchers and leadership to monitor safety.

Skills

Python

PyTorch

NLP

Multimodal models

Data pipelines

Evaluation benchmarks

Distributed systems

LLMs

Education

Bachelor's degree in CS or related field

PhD in CS/ML

Job description

Meta in Menlo Park is seeking a Research Engineer for the Safety Evaluation team within Meta Superintelligence Labs. You will design evaluations that measure safety across text, image, voice, video, and agentic systems, and build the infrastructure to run them continuously through training checkpoints and production traffic.

Join a team shaping measurement standards that gate launches and influence roadmaps across the AI portfolio, mentoring engineers and partnering with Policy, Legal, and