The Autumn 2026 program will run for 10 weeks in Berkeley, CA and London, UK from September 28th to December 4th. Fellows will receive mentorship from world-class researchers and at organizations like Anthropic, Google DeepMind, OpenAI, Redwood Research, and ARC, with the option to apply for a 6–12 month funded extension beyond the main program. For the first time, we are running Founding & Field-Building and Biosecurity tracks.
Applications are now open. Apply by June 7th.

Key dates for the application and admissions timeline
General Application (May 12th to June 7th)
Applicants fill out a general application to individual tracks which should take 1-2 hours. Applications are due by June 7th EOD AOE.
Additional Evaluations (June 7th to late July)
After an initial evaluation, applicants will apply to individual streams listed below. Additionally, applicants undergo a variety of track specific evaluations including coding tests, writing reviews, work tests, and interviews. Which evaluations you will undergo depend on the tracks, streams and mentors you apply to.
Admissions Decisions (Late July to early August)
Selected applicants are notified of their acceptance and anticipated mentor later in the application cycle.

The main program takes place from September 28th to December 4th of 2026. It is an intensive research phase, where fellows work full time on a research project in AI alignment, security, field-building, or governance. Fellows' research directions will typically be chosen through a collaborative process with their mentors, and fellows are expected to develop their independent research direction as the program continues.
While mentor support will vary depending on the project and mentors, mentors are expected to spend at least 1 hour/week working with each of their scholars, and some spend much more time. Scholars will also receive support from MATS’s Research Management team, who help to scope out and structure research direction. Depending on which stream you participate in, you may collaborate with other fellows in your stream.
By the middle of the program, fellows will be expected to write a report on their projects’ threat model, theory of change, and project deliverables. At the end of the program scholars will be expected to have a tangible research output. In past cohorts, this has involved presenting at a fellow symposium on work conducted over the course of MATS.
Educational seminars and workshops will be held 2-3 times per week. Previously, speakers have included Buck Shlegeris from Redwood Research, Adam Gleave from FAR AI, Neel Nanda from Google DeepMind, William Saunders from OpenAI, Andrew Critch from CHAI, Lennart Heim from GovAI, Ajeya Cotra from Open Philanthropy, and more.
The extension phase starts in December of 2026, soon after the end of the main program. Fellows who demonstrate promise as independent researchers during the main program can apply for the MATS extension phase. Acceptance into the extension is based on mentor evaluation and MATS review of proposed research.
In recent cohorts, ~80% of fellows who apply have been accepted. The extension phase offers a default additional 6-months of funding, with the ability to later apply for a 6-month continuation.
Extension fellows primarily work from the MATS London or Berkeley offices, with the possibility of working from other AI safety hubs or fully remotely.For accepted extension fellows, MATS arranges funding for stipends and housing ($7,680/month), as well as for compute ($8,000/mo), creating a seamless transition into this advanced phase of the program.
MATS aims to accelerate researchers who will:
MATS alumni have gone on to publish safety research, join alignment organizations, including Anthropic and MIRI, and found an alignment research lab. You can read more about MATS alumni here.
In stage one, you apply to one or more tracks (broad research areas): Empirical, Theory, Strategy & Forecasting, Policy & Governance, System Security, Biosecurity, and Founding & Field-Building. In stage two, advancing applicants choose specific streams within those tracks, each led by one or more mentors with their own research agenda. You can view this list as a grid here.
Additional streams will be added over the course of May.
We are looking for fellows with a significant background in the biological sciences and/or a founder's perspective to work on and support the Bio Action Plan.
I am looking for fellows with a significant background in the biological sciences and expertise in bio security would be a bonus. A knowledge of public health and pandemic preparedness would also be a bonus. An interest in and strong opinions on these things will be very helpful. I'm also looking for a fellow to take a founder's perspective towards building and organization which can be effective at turning a plan into a reality.
This stream will focus on monitoring, stress-testing safety methods, and evals, with a focus on risks from scheming AIs. Examples include (black-box) AI control techniques, white-box monitors (probes etc.), chain-of-thought monitoring/faithfulness, building evaluation environments, and stress-testing mitigations.
This varies a bit by mentor, but generally we expect fellows to autonomously drive their project forward (alongside their teammate(s)) and meet with their mentor once a week.
Fellows are responsible for:
Mentors are responsible for:
In addition to weekly meetings, you may set up ad hoc meetings with your mentor, reach them on Slack, or send them proposals / paper drafts for review. All meetings will be at times compatible with the BST / CEST timezones.
We're looking for fellows who want to dedicate their careers to making transformative AI go well, and who have strong technical skills. You don't need to be exceptional at every technical skill below, but you should have basic competence across the list and be excellent (or improving fast) in some of them.
Mission orientation
Technical skills
Working style
Team player: You impartially consider others' ideas, disagree respectfully, admit when you're wrong, and commit to the team's direction once decided. You are happy to work in teams of 2-3.
Close to program start, we will share a list of proposed projects, each tied to a primary mentor (some projects may also have a secondary mentor). You will then have some time to think, look up relevant literature, ask mentors questions and talk to other fellows. Then we will send out a form for you to indicate your top N projects, ranked, as well as any teammate or mentor preferences. We will then optimise fellow allocation into teams and projects to maximally satisfy everyone’s preferences.
This stream will focus on projects related to biosecurity countermeasures.
1 hour weekly meetings by default for high-level guidance. Onboarding to our slack, which has access to the entire Blueprint Biosecurity team. Can be reached async every day and can meet as needed.
Successful fellows likely have some sort of a technical background (e.g. technical undergraduate degree), have familiarity with reading research papers, are agentic, prioritize truthseeking, and focused on maximizing impact.
Relevant biosecurity experience is a plus, but not required.
We are very focused on advancing priority countermeasures quickly. We anticipate having projects only focus on these areas:
Within these areas there is some latitude for different projects.
This stream focuses on lead independent research in one of six chokepoints for biotech governance: live pathogen repositories, CROs, cloud labs, cell-free expression systems, plasmid vendors, or secondhand lab equipment.
On high-conviction areas, you'll tackle specific open research questions and assess interventions; on low-conviction areas, you'll conduct deep dives to determine whether they're worth pursuing. Your findings will directly shape Sentinel's grantmaking strategy and provide strategic guidance to the broader biosecurity community.
I'll hold a one-hour weekly check-in by default, with higher frequency during onboarding. I'm available via Slack with quick turnarounds on async messages, and you can schedule ad-hoc calls as needed.
If I bring on multiple fellows or external contractors, I'll add a weekly all-hands to make sure everyone has situational awareness.
Essential:
Preferred:
-Specific chokepoint experience: Familiarity with cloud labs, CROs, live pathogen repositories, cell-free systems, plasmid synthesis, or lab equipment ecosystems is a plus.
-Technical writing and translation skills: You can synthesize complex technical findings for policymakers and other non-technical stakeholders.
While fellows will have some flexibility in selecting the chokepoint they focus on (based on their background and interests), we've designed specific projects and open research questions for each chokepoint to shape their contributions.
Implementing SL4/5 and searching for differentially defense-favored security tools.
I love asynchronous collaboration and I'm happy to provide frequent small directional feedback, or do thorough reviews of your work with a bit more lead time. A typical week should look like either trying out a new angle on a problem, or making meaningful progress towards productionizing an existing approach.
Essential:
Preferred:
Mentor(s) will talk through project ideas with scholar, or scholar will pick from a list of projects.
We are excited to supervise projects:
Essential knowledge:
Essential experience:
Desired experience:
Bonus:
Lee's stream will focus primarily on improving mechanistic interpretability methods for reverse-engineering neural networks.
Mentorship looks like a 1 h weekly meeting by default with approximately daily slack messages in between. Usually these meetings are just for updates about how the project is going, where I’ll provide some input and steering if necessary and desired. If there are urgent bottlenecks I’m more than happy to meet in between the weekly interval or respond on slack in (almost always) less than 24h. We'll often run daily standup meetings if timezones permit, but these are optional.
As an indicative guide (this is not a score sheet), in no particular order, I evaluate candidates according to:
In the past cohort I chose a diversity of candidates with varying strengths and I think this worked quite well. Some mentees were outstanding in particular dimensions, others were great all rounders.
In general I'd like projects in my stream should at least be conceptually informed by parameter decomposition, manifolds, and minimum description length framings of interpretability, if not build on them directly.
Scholars and I will discuss projects and come to a consensus on what feels like a good direction. I will not tell scholars to work on a particular direction, since, in my experience, intrinsic motivation to work on a particular direction is important for producing good research.
The SL5 Task Force will build out a prototype SL5 datacenter this year together with frontier AI labs. This will be a massive research and engineering project with many avenues for spinning out new organizations and research programs. This project is urgent due to this technology being needed in the next 1 to 2 years.
We will meet at least 1h a week synchronously and communicate daily via standard-ups on slack. I typically respond within a few hours for additional feedback and within 1-3 days for indepth code or other review. Scholars can also schedule adhoc calls with me or my co-mentor Luis if they're stuck.
You may have the option to join company meetings and work from our offices 1+ days a week to collaborate with SL5 engineering staff.
This stream is best for strong technical IC's looking to move into research lead / tech lead / org lead positions in the future.
Essential:
Preferred:
Not a good fit:
MATS Research phase provides scholars with a community of peers.

Scholars work out of a shared office and are supported by the Community Team.
MATS alumni report that the connections with peers that they made during MATS have had the largest impact on them years later. Our full-time Community Team works to facilitate these connections and also provide general well-being support. Weekly lightning talks, scholar-led discussion groups, game nights, and outings to SF are some examples of MATS events.