Alumni

Where do people who complete the Iliad Intensive and Iliad Fellowship end up going?

Dan MacKinlay

Dan MacKinlay

Co-founder and Researcher
Alignment Journal and ACS Research
Read bio
PIBBSS × Iliad Research Residency

Dan is a scientist of algorithms. He studies causal and counterfactual machine learning methods: creating algorithms that reason about how the world might be, not merely how it was when the model was trained. He has successfully used this to create state of the art physics-informed AI across problems in geospatial data analysis, advanced manufacturing, mineralogy, viral media dynamics and audio signal processing. He's currently deploying these skills to include understanding agentic AI; How do AI agents reason about the world? When and how can humans coexist them them? How may we safely use, and be used by, them? How can such agents understand the physics of the world in which they act.

Website
Giorgio Frangi

Giorgio Frangi

Researcher
Principia
Read bio
PIBBS x Iliad 2026 Research Residency

Giorgio completed his PhD in theoretical high-energy physics at the University of Edinburgh's Higgs Centre for Theoretical Physics, where he researched various topics in the intersection between quantum field theory, gravity and statistical physics. He is now a researcher working on AI alignment and deep learning theory at Principia.

Dr. Aaron Gutknecht

Aaron Gutknecht

Researcher
XOR Labs
Read bio
August 2026 Iliad Intensive

Aaron develops mathematical methods to study how intelligent systems represent, transform, and use information, with applications ranging from neural data analysis to AI interpretability and safety.

Website

Satya Benson

Research Lead
Iliad
Read bio
Summer 2026 Iliad Fellowship

Satya co-leads Iliad's Agency Research Group. His research centers on information theoretic approaches to understanding abstractions. He holds a BA in Mathematics and Cognitive Science from Williams College.

Leonard Bereska

Teaching & Delivery Lead
Iliad
Read bio
June 2026 Iliad Intensive

Leonard’s background is physics — he briefly worked in theoretical neuroscience, then completed an AI Safety PhD in mechanistic interpretability. He helped the AI Safety Initiative Amsterdam come to life. He joined the June 2026 Iliad Intensive as a participant, and now wants to make the teaching as good as the content deserves and to find talented participants.

Daniel Chiang

Research Lead
Iliad
Read bio
PIBBS x Iliad 2026 Research Residency

Daniel is a Research Lead at Iliad. His research area includes information-theoretic abstractions, logical uncertainty, understanding meta-learning and recursive self-improvement, emergence of continuity through probabilistic structures, mechanism design, and safe pareto-improvements. He has a Msc in Applied Mathematics from Imperial College London.

Julián Szereszewski

Julián Szereszewski

Research Fellow
BAISH Labs
Read bio
PIBBS x Iliad 2026 Research Residency

Julián is a Physicist from the University of Buenos Aires (UBA), with 5+ years of experience in the software industry. He is now a research fellow at BAISH Labs. He is currently doing research around the universality of some safety relevant model behaviors, like personas or scheming. Currently testing this both with the tools used in the platonic representation hypothesis and via model stitching.

Website
Margot Stakenborg

Margot Stakenborg

Research Collaborator
XOR Labs
Read bio
April 2026 Iliad Intensive, Summer 2026 Iliad Fellowship

Margot has worked on various space exploration-related research. She has worked on the attitude and orbit determination, algorithm design, and calibration of the Io-1 nanosatellite, designed to measure the geomagnetic field. She's now interested in working in AI safety; she was an Iliad Fellow in Summer 2026, and is currently an Astra Strategy Fellow.

Website
Franz Nowak

Franz Nowak

Research Collaborator
XOR Labs
Read bio
PIBBS x Iliad 2026 Research Residency

Franz is a PhD student in Computer Science and Natural Language Processing at ETH Zürich. He studied Computer Science at Cambridge, then spent two years working in the software industry before returning to academia for a master's degree and PhD at ETH. In his research, he focuses on using algebraic automata theory and computational mechanics to explore the expressive capabilities and internal mechanisms of reasoning in LLM architectures.

Website

Interested in joining them?

The Research Fellowship: dates, locations, and how to apply.

→ Explore the Fellowship