Sunishchal Dev
This stream will focus on evaluation science, CBRN capability benchmarks, and automated red-teaming.
Stream overview
Science of evaluations, creating novel benchmarks for threat model relevant capabilities (i.e. CBRN), automated redteaming frameworks for CBRN threat assessment
Mentors
Washington, D.C.
—
Biosecurity
Capability and Propensity Evaluations
Sunishchal Dev is an AI evaluations research scientist focused on assessing biological and chemical risks from frontier AI models. Previously, Dev worked in data science and management consulting on enterprise AI and climate solutions.
Mentorship style
Fellows we are looking for
Project selection
The Winter 2026 cohort offers a wide range of research streams led by experts across AI alignment, interpretability, governance, and safety. Each stream provides its own research agenda, methodology, and mentorship focus.
Boston
Policy and Governance
Adversarial Robustness, Policy & Governance, Red-Teaming, Safeguards
London
Control, Monitoring, Safeguards, Dangerous Capability Evals, Scheming & Deception
London
Monitoring, Adversarial Robustness, Control, Model Organisms, Red-Teaming, Dangerous Capability Evals, Safeguards
New York City
Policy and Governance
Dangerous Capability Evals, Control, Strategy & Forecasting, Policy & Governance, Scalable Oversight, Agent Foundations
SF Bay Area
Empirical
Theory
Dangerous Capability Evals, Adversarial Robustness, Security, Red-Teaming, Scalable Oversight
