Eric Wallace

Eric Wallace is a researcher at OpenAI, where he co-leads the Alignment Training team and works on safety, robustness, and privacy for large language models. He completed his PhD in Computer Science at UC Berkeley in 2024 under advisors Dan Klein and Dawn Song, with a thesis focused on emerging vulnerabilities of large language models. He is best known for his research on adversarial attacks, prompt injection defenses, the instruction hierarchy, and memorization risks in production LLMs.