Senior Research Scientist/Engineer, Deception

ABOUT US

The company [link for members] is a non-profit AI research institute working to ensure advanced AI is safe and beneficial for everyone. Our mission is to facilitate breakthrough AI safety research, advance global understanding of AI risks and solutions, and foster a coordinated global response.

Since our founding in July 2022, we've grown to 50+ staff [link for members] published 40+ academic papers [link for members] and convened leading AI safety events [link for members] Our work is recognized globally, with publications at premier venues such as NeurIPS, ICML including a Best Paper Honorable Mention in 2026 [link for members] and ICLR, and features in the Financial Times [link for members] Nature News [link for members] Wired Magazine [link for members] and MIT Technology Review [link for members] We conduct pre-deployment testing on behalf of frontier developers such as OpenAI, independent evaluations for governments including the EU AI Office [link for members] and publish the AI Security Leaderboard [link for members] based on our red-teaming expertise. We help steer and grow the AI safety field through developing [link for members] research [link for members] roadmaps [link for members] with renowned researchers such as Yoshua Bengio; running FAR.Labs [link for members] an AI safety-focused co-working space in Berkeley housing 40+ members; and supporting the community through targeted grants [link for members] to technical researchers.

ABOUT THE TEAM

We explore promising research directions in AI safety and scale up only those showing a high potential for impact. When an approach proves effective, we develop it into a minimum viable demonstration and work with AI developers and governments to support real-world adoption.

Our recent and ongoing research includes

• Mitigating AI deception: studying when lie detectors induce honesty or evasion [link for members] and developing approaches [link for members] to state of the art falsehood detectors [link for members] and sandbagging.

• Red-teaming: conducting pre- and post-release adversarial evaluations of frontier models (e.g. Claude 4 Opus [link for members] ChatGPT Agent [link for members] GPT-5 [link for members] developing novel attacks [link for members] to support this work.

• Evals: developing evaluations for new threat models, e.g. persuasion [link for members] and tampering risks [link for members] and launching a new research agenda on eval awareness

• Applied Interpretability: using interpretability to tackle concrete safety problems (better probes, backdoor detection, deception monitoring), aiming for fast feedback loops, often in collaboration with our other pods.

• Adversarial Robustness: working to rigorously solve security problems through building a science of security and robustness for AI, from demonstrating superhuman systems can be vulnerable [link for members] to scaling laws for robustness [link for members] and jailbreaking constitutional classifiers [link for members]

• Mechanistic Interpretability: finding [link for members] issues [link for members] with [link for members] Sparse Autoencoders, probing deception using AmongUs [link for members] understanding learned planning [link for members] in SokoBan, and interpretable data attribution.

ABOUT THE ROLE

We are looking for an experienced research scientist/engineer to partner with the Research Lead of the Deception team. You’ll lead research projects from initial proposal to implementation, with scope to contribute across multiple projects and teams.

The team works on the following directions

• Detecting deception. Developing white-box probes to identify deception from internal activations, assess failure modes, compare with black-box monitors, and study the effects of self-rationalization.

• Monitoring deployed models. Turning probes into real-time monitors with low false-positive rates, minimal overhead, and reliability across tasks and model versions.

• Training for honesty. Using probes as a training signal and testing whether models become more honest or simply better at concealing deception.

We’ve shown results on an experimental scale, and the next step is scaling them up to a level where frontier labs can adopt them. In addition to providing research judgment, you’ll lead that scaling work and help turn results into methods other teams can use.

WHAT YOU'LL DO

• Lead research projects on various timescales on white-box deception detection, probe-based monitoring, and training against probes. Responsibilities include defining research questions, setting milestones, choosing experiments, and assessing the quality of results.

• Run post-training and RL experiments on large models, including RLVR and fine-tuning with probe-based penalties; diagnose training instability, reward hacking, and infrastructure failures.

• Design model organisms that stress-test methods against realistic failure cases.

• Mentor Members of Technical Staff to strengthen research judgment and experimental rigor.

• Partner with the infrastructure team to plan and run large post-training jobs on the company [link for members] compute cluster.

• Enable frontier labs to adopt the team’s methods through reproducible code, clear evaluations, practical guidance, and direct collaboration with lab safety teams.

• Write and present findings for research papers, frontier lab partners, and the broader AI safety community.

REQUIREMENTS

• 3+ years experience with implementing post-training, model 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.

If you meet most of this and not all of it, we encourage you to apply anyway.

ADDITIONAL SKILLS WE'RE EXCITED ABOUT

Real depth in one or more of these makes you a compelling candidate

• Safety or alignment research at a frontier lab or a research lab working on large models (1T+ parameters)

• Experience with interpretability or white-box methods (e.g probes, steering or SAEs)

• Experience building model organisms of misalignment, or studying reward hacking, scheming or evaluation awareness.

• Publications at top ML venues (NeurIPS, ICML, ICLR) or widely cited technical reports.

• A PhD in a relevant field.

LOGISTICS

If based in the USA or Singapore, you will be an employee of the company [link for members] (501(c)(3) research non-profit / non-profit CLG). Outside the USA or Singapore, you will be employed via an EOR organisation on behalf of the company [link for members] or as a contractor.

• Location: Both remote within U.S. time zones and in-person (Berkeley, CA) are possible. We sponsor visas for in-person employees.

• Hours: Full-time (40 hours/week).

• Application process: 1 short intake call with a technical recruiter, 1 30 minute screening call with the Head of Engineering, a 60 min ML assessment, a 60 min code review interview, a team fit assessment with the hiring manager, and a paid work trial lasting up to 1 week. If you are not available for a work trial we may be able to find alternative ways of testing your fit.

If you have any questions about the role, feel free to contact us at [link for members] Otherwise, if you don't have questions, the best way to ensure a proper review of your skills and qualifications is by applying directly via the application form. Please don't email us to share your resume (it won't have any impact on our decision). Thank you!