Robert Wallach is an AI red team researcher and evaluation specialist with eight years of experience probing frontier LLMs for prompt injection, jailbreaks, bias, and novel failure modes. He blends editorial rigor from an MA in Writing with operational experience scaling an API startup from 4 to 60 employees, giving him a rare ability to translate qualitative textual analysis into systematic adversarial methodologies. Robert discovered "Ecosystem Complement Blindness" in a major production classifier and is building a Python multi-agent research pipeline that applies Hegelian dialectics to evaluation—evidence of an unconventional, theory-driven approach to practical safety testing. Comfortable running local LLM stacks and mapping work to frameworks like MITRE ATLAS and NIST AI RMF, he focuses on conversational inauthenticity detection and reproducible red-teaming playbooks. Now based in the DC–Baltimore area, he’s seeking full-time roles in AI safety, red-teaming, evaluation, or policy research.
8 years of coding experience
5 years of employment as a software developer
Brown Writer's Symposium, Brown Writer's Symposium at Brown University
Environmental Sciences, Environmental Sciences at NOLS
Master of Arts (M.A.), Writing, Literature, and Publishing, Master of Arts (M.A.), Writing, Literature, and Publishing at Emerson College
Bachelor of Arts (B.A.), English Language and Literature, General, Bachelor of Arts (B.A.), English Language and Literature, General at Marymount University
High School Diploma, 2006, High School Diploma, 2006 at Landon School
Contributions:753 commits, 81 PRs, 850 pushes in 1 year 7 months
stoplight
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.
Request Free Trial
Robert Wallach - AI Red Team Researcher & Evaluation Specialist