AI Safety Researcher Resume Example

“AI safety researcher with 4+ years working on alignment, interpretability, and robustness of large language models. Published at top venues on topics including reward hacking, adversarial robustness, and scalable oversight, with experience translating safety research into production guardrails at major AI labs.”

• Published 8 papers on AI safety at NeurIPS, ICML, and FAccT with 1,500+ citations. Topics include alignment, interpretability, and robustness
• Designed the red teaming framework used to evaluate 3 major model releases. Found 200+ failure modes across 15 risk categories
• Built interpretability tools that visualize attention patterns and feature activation in transformers. 20+ researchers use them now
• Developed an automated evaluation suite testing alignment across 1,000+ scenarios. It's now the standard pre-release safety check
• Contributed to the constitutional AI methodology that reduced harmful outputs by 85% while keeping helpfulness scores intact
• Responsible for designing evaluation benchmarks that test for specific safety properties like truthfulness, refusal, and instruction following
• Worked with the policy team to translate technical safety findings into guidelines for model deployment decisions
• Ran experiments on reward hacking and specification gaming. Published findings on how models can exploit reward signals in unexpected ways
• Participated in cross-org safety reviews before major model launches. Provided technical input on risk assessment and mitigation

Include these keywords in your resume to pass Applicant Tracking Systems.

• Ph.D. in Computer Science/AI Safety
• Alignment Forum Contributor