Applications are Open for MATS Research Program – AI Alignment & Security Fellowship 2026/2027

Application Deadline: September 4, 2026

About the Program

The MATS Program is an independent research fellowship that connects talented researchers with top mentors in the fields of AI alignment, transparency, and security. Fellows conduct research for 12 weeks at our offices in Berkeley, CA and London, UK, with the opportunity to apply for an additional 6-12 month funded extension. MATS aims to find and train talented individuals for what we see as the world’s most urgent and talent-constrained problem: reducing risks from unaligned artificial intelligence (AI). We believe that ambitious researchers from a variety of backgrounds have the potential to meaningfully contribute to the field of alignment research.

Program Features

• Mentorship: Fellows receive guidance from top researchers in AI alignment, governance, and security
• Research Support: Fellows work with a dedicated research manager who helps scope projects, maintain progress, and remove blockers
• Educational Events: Fellows participate in seminars, workshops, and guest lectures led by experts across the alignment community
• Stipend: Fellows receive a $1,250 stipend per week to cover expenses
• Compute Budget: Fellows are provided with $2,000 per week of compute resources to support experiments and evaluations
• Workspace: Fellows have access to office space in Berkeley and London, and collaborate daily with fellow researchers
• Meals & Housing: Fellows receive catered lunches and dinners and are provided with housing for the full duration of the main program
• Community: Fellows gain connections and networking opportunities across the broader AI alignment ecosystem
• Extension Pathway: Fellows may apply to join the London-based extension program for an additional 6–12 months of research; over 80% of fellows are admitted

Why This Program Matters

MATS provides a structured pathway for talented researchers to enter the field of AI alignment and security. By offering mentorship, research support, community, and financial stability, the program enables fellows to focus on solving one of the most urgent problems of our time. Alumni have gone on to lead research at major AI labs, found new organisations, and publish influential papers that shape the field.

For aspiring researchers with a strong interest in AI alignment, transparency, and security, MATS offers:

• Expert mentorship from top researchers
• Generous stipend and compute budget
• Collaborative research environment in Berkeley and London
• Pathway to extension for 6–12 months of additional research
• Career connections to leading organisations
• A community of talented, motivated peers

Program Impact

Since late 2021, over 527 researchers have trained through MATS, producing 200+ research papers with over 12,000 collective citations. The organizational h-index is 50. 80% of alumni are now working in AI alignment, transparency, and security. MATS alumni have been hired by leading organisations like Anthropic, Google DeepMind, OpenAI, Meta AI, UK AISI, Redwood Research, METR, RAND CAST, Coefficient Giving, ARC, FAR.AI, Apollo Research, Truthful AI, Goodfire, LawZero, MIRI, CAIF, Centre on Long-Term Risk, Beneficial AI Foundation, SaferAI, Haize Labs, EleutherAI, Harmony Intelligence, Conjecture, and joined academic research groups like UC Berkeley CHAI, NYU ARG, NU Bau Lab, Mila, and MIT Tegmark Group.

Research Tracks

MATS fellows’ core work focuses on tracks including:

• AI Safety: Ensuring powerful AI systems follow human intentions
• AI Security: Hardware-enabled governance and preventing the theft of model weights
• AI Policy: Governing the development of transformative AI
• Interpretability: Reverse-engineering neural networks and their internal representations
• Biosecurity: Preventing or preparing for AI-enabled bioattacks
• Societal Impacts: Understanding the effect of transformative AI on society and the economy

Key Dates

• Neel Nanda’s Stream Applications: Open now until September 4, 2026
• Full Winter 2027 Application: Launches soon (fill out the form on the website to be notified)

Eligibility

The program is open to ambitious researchers from a variety of backgrounds who have the potential to meaningfully contribute to the field of alignment research. Specific eligibility criteria vary by mentor stream and track.

How to Apply

Application Link: Click here to apply

For More Information: Visit the Official MATS Program Website