Fellowship · 10a Labs

10a Labs Red Teaming Fellowship

Hands-on AI safety, security, and adversarial testing fellowship for frontier models and AI-enabled systems

open yes, continental U.S. remote

Program overview

Strong fit for model behavior testing, adversarial evals, prompt attacks, leakage/redaction and actionable reports

Notes

Pair resume with support-agent safety gates and production LLM regression tests

View official program ↗