Senior Research Scientist/Engineer, Deception
FAR.AIBerkeley Office, Remote (US), Remote (International)On-Site
Needs a free Superjobs account. You'll finish on FAR.AI's Ashby page.
Skill score
Summary
The person in this role leads research projects on white-box deception detection, probe-based monitoring, and training for honesty, and takes on the work of scaling these methods so frontier labs can adopt them. It suits an experienced researcher or engineer with hands-on large-model post-training experience and strong research judgment.
- Function
- Development
- Estimated salary
- Est. $135k–202k/yr
- Estimated for a senior role, ~3 yrs experience, United States. Not published by the employer.
- Work mode and location
- On-Site, Berkeley Office, Remote (US), Remote (International)
- Experience
- 3+ yrs
- Employment type
- Full-time
Job description
Overview
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, and developing approaches to state of the art falsehood detectors and sandbagging.
- Red-teaming: conducting pre- and post-release adversarial evaluations of frontier models (e.g. Claude 4 Opus, ChatGPT Agent, GPT-5); developing novel attacks to support this work.
- Evals: developing evaluations for new threat models, e.g. persuasion and tampering risks, 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, to scaling laws for robustness and jailbreaking constitutional classifiers.
- Mechanistic Interpretability: finding issues with Sparse Autoencoders, probing deception using AmongUs, understanding learned planning in SokoBan, and interpretable data attribution.
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.
Roles and responsibilities
- 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 http://FAR.AI’s 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.
Skills required
Top skills
- post-training
- reinforcement learning
- RLHF
- RLVR
All skills (8)
- fine-tuning
- Python
- PyTorch
- research judgment
- interpretability
- probes
- model organisms
- sparse autoencoders
Qualifications
- 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.
Nice to have
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.
Other details
If based in the USA or Singapore, you will be an employee of http://FAR.AI (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 http://FAR.AI 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 [email protected]. 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!
Company info
About FAR.AI
http://FAR.AI 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