Research Scientist at FAR.AI

This role is ideal for mid-to-senior level researchers with a PhD or equivalent experience in Machine Learning who are passionate about AI safety. It is a parti

Work type: remote

Location: Berkeley Office | Remote (International) | Remote (US)

Salary: $120,000 – $190,000/yr

Type: Full-time

Summary

This role is ideal for mid-to-senior level researchers with a PhD or equivalent experience in Machine Learning who are passionate about AI safety. It is a particularly good fit for "unconventional" candidates—those who have their own research agendas or a strong desire to transition from general ML into safety-specific areas like red-teaming, mechanistic interpretability, or adversarial robustness. The position offers rare flexibility for a research role, including fully remote options (US and International) or an in-person environment in Berkeley (and soon Singapore). Compensation is competitive for the non-profit sector ($120k–$190k), and the culture emphasizes "research freedom" that bridges the gap between slow-moving academia and product-focused corporate labs. You’ll benefit from high-end GPU clusters and opportunities to collaborate directly with national AI safety institutes and frontier model labs. **You might be a good fit if you...** * Have a strong track record of publishing at top-tier conferences like NeurIPS, ICLR, or ICML. * Want to move beyond theory and build "minimum viable prototypes" that influence AI policy and corporate deployment. * Are proficient in Python and comfortable with a rigorous technical hiring process, including a 72-minute coding test and a paid work trial. * Are excited about developing novel attacks or "lie detectors" for LLMs.

Job Description

## About Us

[FAR.AI](http://FAR.AI) is a non-profit AI research institute dedicated to ensuring 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. Founded in July 2022, we have grown quickly to [40+ staff](https://www.far.ai/about/team). We are uniquely positioned to conduct technical research at a scale surpassing academia and leveraging the research freedom of being a non-profit. Our work is published at top conferences (e.g. NeurIPS, ICLR, ICML) and cited by leading media outlets such as the [Financial Times](https://www.ft.com/content/175e5314-a7f7-4741-a786-273219f433a1), [Nature News](https://www.nature.com/articles/d41586-024-02218-7) and [MIT Technology Review](https://www.technologyreview.com/2020/02/28/905615/reinforcement-learning-adversarial-attack-gaming-ai-deepmind-alphazero-selfdriving-cars/).

[FAR.AI](http://FAR.AI) uses three prongs working together to improve AI safety:

• FAR.Research - we conduct cutting-edge AI safety [research](https://www.far.ai/research) in-house and [dispense grants](https://www.far.ai/programs/grantmaking) to support the wider research community.

• FAR.Futures - we bring together key policy makers, researchers and companies to drive change, such as the [San Diego Alignment Workshop](https://www.far.ai/events/event-list/san-diego-alignment-workshop) or the Guaranteed Safe AI [research roadmap](https://arxiv.org/abs/2405.06624) written with Yoshua Bengio.

• FAR.Labs - we host a co-working space in Berkeley to help to incubate other AI safety organizations, currently housing 40 members.

We explore promising research directions in AI safety and scale up only those showing a high potential for impact. Once the core research problems are solved, we work to scale them to a minimum viable prototype, demonstrating their validity to AI companies and governments to drive adoption.

We are aiming to rapidly grow our team in the following areas especially, at varying levels of seniority:

• Evals and 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; and exploring new threat models (e.g. [persuasion](https://arxiv.org/abs/2506.02873), [tampering risks](https://arxiv.org/abs/2507.11630)).

• Infrastructure:Maintaining GPU compute infrastructure to support experiments with open-weight models and developing new tooling to allow our research teams to scale their fine-tuning and post-training workflows to frontier open-weight models.

• Mitigating AI deception: Studying when [lie detectors induce honesty or evasion](https://www.far.ai/news/avoiding-ai-deception), and developing model organisms for deception and sandbagging

• Adversarial Robustness: Working to rigorously solve these 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: F[inding](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 organize our team as Members of Technical Staff, with significant overlap between scientist and engineer roles. As a scientist, you will take ownership of and accelerate existing AI alignment research agendas. You can publish research findings broadly and engage with the AI alignment community. If you are an experienced research scientist, then we would be excited to incubate your agenda at FAR using our existing infrastructure and world-class team.

You will receive engineering mentorship via code review, pair programming and regular 1-to-1s. Alongside the engineers, you will be involved in develop scalable implementations of machine learning algorithms and using them to run scientific experiments,

You are encouraged to develop your research taste, proposing novel directions and joining a research pod which suits your interests. You are welcome to take time to study and to attend conferences free of charge. Our technical team is organized into research pods to enable continuity of organizational structure whilst each pod can pivot through varied research projects.

Beyond [FAR.AI](http://FAR.AI), you can work with national AI safety institutes, frontier model developers and top academics.

## About You

We are excited by unconventional backgrounds. You may have the following:

• New and under-explored AI alignment idea(s).

• Experience leading and/or playing a senior role in research projects related to machine learning.

• Ability to effectively communicate novel methods and solutions to both technical and non-technical audiences.

• PhD or several years research experience in computer science, artificial intelligence, machine learning or statistics.

If based in the USA, you will be an employee of [FAR.AI](http://FAR.AI), a 501(c)(3) research non-profit. Outside the USA, you will be an employee of an EoR organization on behalf of [FAR.AI](http://FAR.AI).

• Location:Both remote (global) and in-person (Berkeley, CA) are possible. We are also expecting an in-person Singapore office in 2026Q3 as an alternative location. We sponsor visas for in-person employees, and can also hire remotely in most countries.

• Hours:Full-time (40 hours/week).

• Compensation: $120,000-$190,000/year depending on experience and location. We will also pay for work-related travel and equipment expenses. We offer catered lunch and dinner at our offices in Berkeley.

• Application process: A 72-minute programming assessment, two interviews with members of our technical staff, 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.

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!

View this job on nocollar jobs