Jobs in the United States

25+ jobs

Save this search

Added 1 min ago
MACHINE LEARNING ENGIENEER II (REMOTE)
The Home Depot
Remote, United States
Position Purpose:The Machine Learning Engineer II is responsible for joining a product team and contributing to the software design, algorithm design, and overall product lifecycle for a…
Added 1 min ago
Senior QA Automation Engineer
Planet Depos LLC
Remote, United States
We need a Senior QA Automation Engineer to build the automated tests that tell us, quickly and reliably, whether a change is ready to release. You will sit on one of our product teams and…
Added 3 mins ago
Data Scientist II
BAE Systems
Rockville, MD
- Partner with software engineer, test engineers, test manager, and other stakeholders to translate business needs into technical data solutions
Added 5 mins ago
RU
Senior Backend Engineer - Java / AWS
Randstad USA
Washington, DC
- $60 to $65 USD / hour
Randstad Digital is seeking a Senior Backend Engineer (Java / AWS) to join a core engineering delivery team within a major national passenger transportation organization's Corporate &…
Added 6 mins ago
R
Staff DX Engineer
Render
Remote, United States
- $236,000 to $289,000 USD / year
…We're also often the first real users of what Render ships. We test major releases end to end, the way a customer would, and tell Product and Engineering where they fall down before…
Added 9 mins ago
Automation Test Engineer
Booz Allen Hamilton_United States
Chantilly, VA
…means rigorous testing. That’s why we need you, an experienced test engineer who knows how to thoroughly test software and work with developers to make sure our team releases the best…
Added 10 mins ago
Senior Software Engineer - Lab Automation
Genentech, Inc.
United States
and accelerate decision-making. As a software engineer, you will bridge the gap between scientific workflows and modern software solutions, which may include working alongside laboratory…
Added 10 mins ago
TN
Forward Deployed Engineer - AI Solutions (Gracenote Division)
The Nielsen Company
Remote, United States
- $203,000 to $377,000 USD / year
…-based workflows. Act as "Customer Zero" to familiarize with, test and validate new MCP tools and features before they roll out to…
Added 12 mins ago
CM
Senior Applications Security Engineer (SOAR)
Centene Management Company LLC
Remote, United States
- $87,000 to $161,300 USD / year
Position Purpose: The Senior SOAR Engineer/Developer designs, develops, and maintains security orchestration and automation solutions that improve cybersecurity operations. The role…
Added 12 mins ago
CM
Applications Security Engineer II (SOAR)
Centene Management Company LLC
Remote, United States
- $75,300 to $135,400 USD / year
Position Purpose: The SOAR Engineer/Developer designs, develops, and maintains security orchestration and automation solutions that improve cybersecurity operations. The role develops SOAR…
Added 14 mins ago
Senior Test Infrastructure & Reliability Engineer, Photonics
PsiQuantum
Palo Alto, CA
As an integral part of the team developing a photonic quantum computer, the Senior Test Infrastructure & Reliability Engineer will own the data pipeline and reliability of the systems that…
Added 16 mins ago
Associate Engineer, Investment Data & Analytics
HarbourVest Partners, LLC
United States
…Working under the guidance of senior engineers, you will develop, test, and operate the pipelines and datasets our investment and research teams rely on - taking on progressively more…
Added 17 mins ago
Principal/Sr. Principal Cyber Systems Engineer
CORP-Corporate Office
United States
Northrop Grumman Mission Systems has an opening for a Principal or Sr. Principal Cyber Systems Engineer to join the K2 program. We are seeking a skilled and motivated engineer to support…
Added 17 mins ago
CO
2027 Flight Software Engineer Intern - Redondo Beach CA
CORP-Corporate Office
United States
- $21.5 to $41 USD / hour
Design, develop, document, test and debug applications software and systems that contain logical and mathematical solutions.
Added 17 mins ago
CO
2027 Ground Software Engineer Intern - Redondo Beach CA
CORP-Corporate Office
United States
- $21.5 to $41 USD / hour
Design, develop, document, test and debug applications software and systems that contain logical and mathematical solutions.
Added 17 mins ago
2027 Associate Flight Software Engineer - Manhattan Beach CA
CORP-Corporate Office
United States
Support flight software development across the full life cycle: requirements, design, implementation, test, and deployment
Added 17 mins ago
Configurable On-Board Router (COR) Team - Software Engineer (AHT)
CORP-Corporate Office
United States
Northrop Grumman’s Space Sector is seeking a Software Engineer (Level 1 or 2) to join our team of highly qualified, diverse professionals within the Western Region Software Engineering…
Added 17 mins ago
Mobile Reverse Engineer
Peraton
Bethesda, MD
Peraton is seeking a Mobile Reverse Engineer in our Bethesda, MD office in support of our Department of Defense (DoD) customer as part of a highly talented, highly motivated, and…
Added 18 mins ago
Senior Software Engineer, AI/ML Recommendations, Rankings, Predictions, YouTube
YouTube
Mountain View, CA
5 years of experience programming in Python and C++.
Added 18 mins ago
AI Data Migration Engineer
GovPilot
Remote, United States
…generate cleansing, deduplication, and load scripts. Then review, test, and take ownership of the…
Added 20 mins ago
AI Software Engineering Clinical Systems
CSBio
Milpitas, CA
CSBio and Yowei Therapeutics are seeking a hands-on AI Software Engineer to build internal applications, AI-assisted workflows, data systems, and secure automations supporting clinical,…
Added 20 mins ago
Cloud & Infrastructure - AIOps Engineer (AI Infrastructure Engineer)
Vailexa
Remote, United States
Separate infrastructure faults from workload or test issues and turn findings into clear next steps, remediation actions, and operational guidance.
Added 24 mins ago
Advanced Cyber Security Architect/Engineer
Honeywell
Duluth, GA
As an Advanced Cyber Security Architect/Engineer at the Honeywell Industrial Cybersecurity Centers of Excellent and Innovation, you will lead the research, development, and engineering of…
Added 26 mins ago
S|
Data Engineer II
StorageMart | MMS
Columbia, MO
- $100,000 to $120,000 USD / year
Build, test, and maintain data ingestion and transformation pipelines in Snowflake using native tooling (Snowpipe, Streams and Tasks, Dynamic Tables, Snowpark, external stages, and…
Added 26 mins ago
S|
Data Engineer II
StorageMart | MMS
Columbia, MO
- $100,000 to $120,000 USD / year
Build, test, and maintain data ingestion and transformation pipelines in Snowflake using native tooling (Snowpipe, Streams and Tasks, Dynamic Tables, Snowpark, external stages, and…

FAR.AI

Senior Research Scientist/Engineer, Deception

Berkeley, CA, United States

$225,000 to $350,000 USD / year

Apply About employer

Applications open in a new tab.

Job details

Pay: $225,000 to $350,000 USD / year
Experience: 3+ years experience with implementing post-training, model training, or closely related efforts in a frontier AI environment
Working hours: 40 hours/week
Posting language: English
Posted: Nov 3, 2026

Original job description

ABOUT US

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 50+ staff https://www.far.ai/about/team, published 40+ academic papers https://scholar.google.com/citations?user=FVJ24k8AAAAJ, and convened leading AI safety events https://far.ai/events/. Our work is recognized globally, with publications at premier venues such as NeurIPS, ICML including a Best Paper Honorable Mention in 2026 https://icml.cc/virtual/2026/oral/71065, and ICLR, and features in the Financial Times https://www.ft.com/content/175e5314-a7f7-4741-a786-273219f433a1, Nature News https://www.nature.com/articles/d41586-024-02218-7, Wired Magazine https://www.wired.com/story/jailbreaking-ai-models-google-anthropic-openai-spacexai/ and MIT Technology Review https://www.technologyreview.com/2020/02/28/905615/reinforcement-learning-adversarial-attack-gaming-ai-deepmind-alphazero-selfdriving-cars/. We conduct pre-deployment testing on behalf of frontier developers such as OpenAI, independent evaluations for governments including the EU AI Office https://www.far.ai/news/far-ai-selected-to-lead-eu-ai-act-cbrn-risk-consortium, and publish the AI Security Leaderboard https://leaderboard.far.ai/ based on our red-teaming expertise. We help steer and grow the AI safety field through developing https://arxiv.org/abs/2405.06624 research https://arxiv.org/abs/2506.20702 roadmaps https://www.researchgate.net/publication/396910034_Open_Technical_Problems_in_Open-Weight_AI_Model_Risk_Management with renowned researchers such as Yoshua Bengio; running FAR.Labs https://www.far.ai/programs/far-labs, an AI safety-focused co-working space in Berkeley housing 40+ members; and supporting the community through targeted grants https://www.far.ai/programs/grantmaking 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 https://www.far.ai/news/avoiding-ai-deception, and developing approaches https://www.far.ai/research/the-obfuscation-atlas-mapping-where-honesty-emerges-in-rlvr-with-deception-probes to state of the art falsehood detectors https://arxiv.org/abs/2610.12445 and sandbagging.
Red-teaming: conducting pre- and post-release adversarial evaluations of frontier models (e.g. Claude 4 Opus https://x.com/ARGleave/status/1926138376509440433, ChatGPT Agent https://cdn.openai.com/pdf/839e66fc-602c-48bf-81d3-b21eacc3459d/chatgpt_agent_system_card.pdf, GPT-5 https://cdn.openai.com/gpt-5-system-card.pdf); developing novel attacks https://www.far.ai/news/defense-in-depth to support this work.
Evals: developing evaluations for new threat models, e.g. persuasion https://arxiv.org/abs/2506.02873 and tampering risks https://arxiv.org/abs/2507.11630, 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 https://far.ai/post/2023-07-superhuman-go-ais/, to scaling laws for robustness https://www.far.ai/news/does-robustness-improve-with-scale and jailbreaking constitutional classifiers https://arxiv.org/abs/2506.24068.
Mechanistic Interpretability: finding https://arxiv.org/abs/2502.12892 issues https://arxiv.org/abs/2508.16560 with https://arxiv.org/abs/2505.11756 Sparse Autoencoders, probing deception using AmongUs https://arxiv.org/abs/2504.04072, understanding learned planning https://far.ai/post/2024-07-learned-planners/ 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 FAR.AI 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.

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 FAR.AI 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 FAR.AI 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 talent@far.ai. 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!

Apply About employer

More about this job

Skills

Research
Create model
Collaboration
Python
PyTorch
ML
Logistics

Report this job