Lead AI Safety Research Scientist (Deception & Monitoring)

Ai Safety; Berkeley (CA); Hybrid; USD 180,000 - 260,000; Full time

Benefits offered by this job

Health insurance

Job summary

FAR.AI in Berkeley, CA is seeking an experienced research scientist/engineer to partner with the Research Lead of the Deception team. You’ll lead research projects from proposal to implementation, with scope to contribute across multiple projects and teams.

The role involves detecting deception, monitoring deployed models, and training for honesty, with opportunities to mentor staff and scale results for frontier labs.

Qualifications

• 3+ years experience implementing post-training or closely related efforts in a frontier AI environment.
• Hands-on experience post-training models at scale (RL, RLHF/RLVR or large fine-tuning runs), ideally on models of 400B+ parameters.
• Strong Python and PyTorch, and experience working in large, shared research codebases.
• Strong research judgement to know what experiments to run next and to recognize when a result needs further scrutiny.
• Based in or willing to work in U.S. time zones. In person in Berkeley is preferred.

Responsibilities

• Lead research projects on white-box deception detection, probe-based monitoring, and training against probes.
• Run post-training and RL experiments on large models, including RLVR and fine-tuning with probe-based penalties; diagnose training instability.
• Design model organisms that stress-test methods against realistic failure cases.
• Mentor Members of Technical Staff to strengthen research judgement and experimental rigor.
• Partner with the infrastructure team to plan and run large post-training jobs on FAR.AI’s compute cluster.
• Enable frontier labs to adopt the team’s methods through reproducible code, clear evaluations, and practical guidance.
• Write and present findings for research papers, frontier lab partners, and the broader AI safety community.

Skills

Post-training experience

RL/RLHF/RLVR

Python

PyTorch

Model training at scale

Education

PhD in a relevant field

Job description

FAR.AI in Berkeley, CA is seeking an experienced research scientist/engineer to partner with the Research Lead of the Deception team. You’ll lead research projects from proposal to implementation, with scope to contribute across multiple projects and teams.

The role involves detecting deception, monitoring deployed models, and training for honesty, with opportunities to mentor staff and scale results for frontier labs.