Researcher

Berkeley

What does ARC do?

The Alignment Research Center (ARC) is a non-profit whose mission is to align future machine learning systems with human interests.

ARC's high-level agenda is described by the report on Eliciting Latent Knowledge (ELK): roughly speaking, we’re trying to design ML training objectives that incentivize systems to honestly report their internal beliefs.

For the last couple of years, we have been focused on mechanistically understanding the structure of neural networks in order to be able to estimate their properties more efficiently than can be done with random sampling. We discuss this approach in our blog post, Competing with sampling, and explain how this fits into our broader research agenda in another blog post, A Mike's-Eye View of ARC's Research.

If you want to understand our research agenda in more depth, we recommend first reading the above two posts, followed by:

• Mechanistic estimation for wide random MLPs (NeurIPS 2026)
• Mechanistic estimation for expectations of random products
• A bird's eye view of ARC's research
• Formal verification, heuristic explanations and surprise accounting
• Estimating tail risk in neural networks

Our research has reached a stage where we're overrun with concrete problems in mathematics, theoretical computer science and machine learning, and so we’re particularly excited about hiring researchers with relevant background, regardless of whether they have worked on AI alignment before. We are also investing seriously in AI tools to help accelerate our research, and we expect this to dramatically change how we conduct research over the course of the next year.

(Note: ARC is not to be confused with METR, which was formerly known as "ARC Evals" but has since been spun out.)

Who is ARC looking to hire?

Most successful candidates have a strong theoretical background (in math, physics or computer science, for example). Empirical machine learning background is a plus, but is not required for a strong application.

We also remain open to anyone who is excited about getting involved in AI alignment, even if they do not have an existing research record.

Ultimately, we are excited to hire people who could contribute to our research agenda. One way to figure out whether you might be able to contribute would be to take a look at some of our recent research, as described on our blog.

What is working at ARC like?

ARC currently has six permanent team members (see our team here), with several more planning to join in January, alongside a varying number of temporary team members (recently, anywhere from 2–15).

Most team members work on research problems independently, but with significant collaboration. (A typical researcher spends about 25% of their time collaborating with others.) This work is often somewhat similar to academic research in pure math or theoretical computer science, or machine learning.

In addition to this, we also allocate a significant portion of our time to higher-level questions surrounding research prioritization, which we often discuss at our weekly group meeting. Since the team is still small, we are keen for new team members to help with this process of shaping and defining our research.

ARC shares an office with several other groups working on AI safety such as METR and Redwood Research, so even though our team is small, the office is lively with lots of AI-related discussion.

Hiring process

Our current interview process involves:

- 3-hour take-home test involving math and computer science puzzles

- 30-to-45-minute technical phone screen

- 30-minute non-technical phone call

- 1-day onsite interview

We will compensate candidates for their time when this is logistically possible.

Employment details

ARC is based in Berkeley, California, and we would prefer people who can work full-time from our office, but we are open to discussing remote or part-time arrangements in some circumstances. We can sponsor visas and are H-1B cap-exempt.

We are accepting applications for both visiting researcher (1–3 months) and full-time positions. The intention of the visiting researcher position is to assess potential fit for a full-time role, and we expect to invite around one half of visiting researchers to join full-time. We are also able to offer straight-to-full-time positions, but we anticipate that we will only be able to do this for people with a legible research track-record. We are only be interested in applicants who can start full-time by September 2028 (though sooner is better).

Salaries start at $300k and increase with experience.

\n \n

Further information

If you have any questions about anything in this posting, please email hiring@alignment.org.