Publications: 'The Concordia Contest: Advancing the Cooperative Intelligence of Language Model Agents' (NeurIPS 2024 Competition Track); 'MALT: Improving Reasoning with Multi-Agent LLM Training' (Preprint - AAMAS 2025 Submission). Conference Presentation: Presented 'Better Benchmarks: A Roadmap for High-Stakes Evaluation in the Age of Agentic AI' at the IASEAI '25 Safe & Ethical AI Conference.
Research Experience
Research Engineer at the Cooperative AI Foundation; previously worked as an engineer at Dimagi on global health and COVID response projects; consults with IQT's applied research and technology architect teams on AI, multi-agent systems, and AI infrastructure.
Education
MATS scholar, collaborating with Jesse Clifton on multi-agent systems research.
Background
Research Interests: multi-agent systems, AI safety, steganography, and AI control. Background: Research Engineer at the Cooperative AI Foundation, focusing on technical research related to multi-agent systems. Selected as a 2025 Cooperative AI PhD Fellow and a Foresight AI Safety Grant Recipient.
Miscellany
Can be found on Twitter, LinkedIn, GitHub, Google Scholar, and via Email.