Find your fit in AI safety research

MATS fellows work across seven tracks spanning technical research, governance, biosecurity, strategy, theory, security, and field-building. Explore each track to learn what fellows work on, who the track is for, and how to apply.

Winter 2027 Tracks

View MATS Winter 2027 tracks and their streams.

Founding and Field-Building

AI safety needs to scale fast, and the bottleneck is increasingly organizational. This track is targeted at founders, field-builders, and high-agency generalists launching new AI safety organizations and programs, including projects that are mentored by founders, sitting CEOs, and program directors across the ecosystem.

View track
Juniper Ventures
Dewi Erwan (BlueDot Impact)
Vehbi Deger Turan (Metaculus)
Rosie Campbell (Eleos)
Alex Holness-Tofts (Resolution)
Oliver Habryka (Lightcone)
Matthew Gentzel

Empirical

Hands-on research using machine- learning experiments to understand and improve model safety including AI control, interpretability, scalable oversight, evaluations, red-teaming, and robustness.

View track
David Africa
No items found.
UK AISI Control
Maksym Andriushchenko
Transluce
Team Shard
Redwood Research
Apollo Research - Monitors
Tomek Korbak
Anthropic
Alfie Lamerton & Joe Kwon
Neel Nanda
Joshua Engels
Jacob Merizian
Victoria Krakovna
Cozmin Ududec
Neev Parikh
Apollo Research - Science of Scheming
LawZero
Sydney Von Arx
UK AISI Alignment Red Team
Shi Feng & Eyon Jang
Nathan Lambert -- Character Training
AI Village
Francis Rhys Ward
Patrick Butlin
Andrew Saxe & Nischal Mainali
Daniel Kang
Paul Riechers, Adam Shai
Shafi Goldwasser, Orr Paradise
Juniper Ventures
No items found.
Jo Faraguna
Oliver Crook
SecureBio AI
Abhishek Mishra
Sunishchal Dev
Fourth Eon Biosecurity
LILA (David Peinador Veiga)

Policy and Governance

Research on how advanced AI is and should be governed, spanning governance mechanisms, regulatory and institutional analysis, and the technical systems that make governance enforceable.

View track
Dave Banerjee
Safe AI Forum
Matthew Gentzel
Mauricio Baker, Anjay Friedman
McKenna Fitzgerald
Michael Chen
Patricia Paskov & Miles Brundage (AVERI)
TAIGR
Luke Drago, Rudolf Laine
Leonie Koessler
FAI AI Team
Sambhav Maheshwari, Jan Wehner

Biosecurity

Research on catastrophic biological risk in a world being reshaped by advanced AI. Spans pathogen detection, medical countermeasures, synthesis screening, physical biodefense, threat modeling, and red-teaming biological AI for dangerous capabilities.

View track
Oliver Crook
SecureBio AI
Sebastian Oehm, Askar Kleefeldt
Aman Patel, Adin Richards
Sunishchal Dev
Fourth Eon Biosecurity
LILA (David Peinador Veiga)
Abhishek Mishra
No items found.
Jo Faraguna

Strategy and Forecasting

Research on how AI development is likely to unfold and what that means for long-term safety. Includes timelines, takeoff dynamics, risk modeling, and strategic analysis of AI's trajectory.

View track
Dave Banerjee
Civilizational Alignment
AI Futures Project
Luke Drago, Rudolf Laine
Matthew Gentzel
Vehbi Deger Turan (Metaculus)
Oliver Habryka (Lightcone)

Theory

Foundational research on the mathematical and philosophical principles underlying agency, alignment, and safe reasoning in advanced AI systems.

View track
Alignment Research Center (ARC)
Richard Ngo
Andrew Saxe & Nischal Mainali
Paul Riechers, Adam Shai
Shafi Goldwasser, Orr Paradise
Patrick Butlin

Systems Security

Research on software and hardware security for the infrastructure on which advanced AI runs, including side-channel analysis, cluster security, model-weight protection, and physical-layer verification.

View track
ISL
Lisa Thiergart, Luis Cosio, Guy (SL5 Task Force)
Mauricio Baker, Anjay Friedman
Daniel Kang