Biosafety Red Teaming Specialist
OpenAI · San Francisco, California
- Compensation
- $158k - $320k/yr
- Location
- San Francisco, California, United States
- Workplace
- Remote
- Level
- Mid level
- Posted
- 7 weeks ago
About this role
About the Team The Intelligence and Investigations team seeks to rapidly identify and mitigate abuse and strategic risks to ensure a safe online ecosystem in close collaboration with our internal and external partners. Our efforts contribute to OpenAI's overarching goal of developing AI that benefits humanity. About the Role We are looking for an expert in biological and chemical risks to lead red teaming efforts for biosafety and to help mature OpenAI’s bio bounty programs. You will help shape biology-relevant test plans, guide external and internal engagements, ensure our testing is impactful, and translate findings into clear outcomes. In addition, you’ll play a critical role in driving our bio bounty programs, including managing external researcher relationships, evolving challenge questions, reviewing submissions that require biological subject-matter expertise, and maturing the program as it continues to scale. This role also requires broad and deep CBRN expertise, strong operational judgment or program management experience, and an adversarial mindset. You should be well-versed in understanding how a determined actor might misuse frontier AI systems, while also knowing how to turn sensitive findings into constructive, actionable safety work. In this role, you will - Lead bio red teaming work from a domain perspective, including shaping evaluation questions, scenarios, and success criteria for biology-relevant misuse pathways. - Review and pressure-test bio red teaming outputs, assess report quality, and help translate findings into concise risk calls and recommended next steps. - Identify new red teaming engagements or external expert collaborations that would improve OpenAI's visibility into biological and overall CBRN misuse risks. - Bring an adversarial mindset to assess how malicious actors could attempt to misuse model capabilities across planning, protocol design, procurement, troubleshooting, and operationalization. - Directly manage Bio Bounty program
Excerpt from the posting OpenAI published. Read the full description on their site before applying.
Skills this posting mentions
About OpenAI
OpenAI is an AI research and deployment company dedicated to ensuring that general-purpose artificial intelligence benefits all of humanity. AI is an extremely powerful tool that must be created with safety and human needs at its core. OpenAI is dedicated to putting that alignment of interests first - ahead of profit. To achieve our mission, we must encompass and value the many different perspectives, voices, and experiences that form the full spectrum of humanity. Our investment in diversity, equity, and inclusion is ongoing, executed through a wide range of initiatives, and championed and supported by leadership. At OpenAI, we believe artificial intelligence has the potential to help people solve immense global challenges, and we want the upside of AI to be widely shared. Join us in shaping the future of technology.
All 759 openings at OpenAIApply to this role, tailored
Queue Biosafety Red Teaming Specialist at OpenAI and I will read the posting, rewrite your resume against it, draft the cover letter, and score the fit before you send anything.
Applications finish as drafts. Nothing is sent until you read it and press send. New accounts start with 500 free credits.
More roles at OpenAI
See all- Today
- Today
- 2 days ago
- 3 days ago
- 3 days ago
- 3 days ago
Software Engineer, Agent Productivity
San Francisco, CaliforniaHybrid
$293k - $342k/yrMid levelEngineering
Listed from the job board OpenAI publishes. Refolk is not the employer and does not handle their hiring. Applications go to OpenAI directly.