Senior Software Engineer, AI Benchmarking

Build and scale biosecurity evaluations to assess dual-use biology risks in frontier AI systems.
- Perform pre-release and post-release assessments of frontier AI models using SecureBio's biosecurity evaluation suite.
- Build, scale, and improve evaluations using state-of-the-art agent frameworks, jailbreaking methods, and elicitation strategies.
- Develop internal tools and cloud infrastructure enabling researchers to run capability assessments at scale.
- Requires 5+ years software engineering experience, Python fluency, and Docker/AWS proficiency.
- Experience building tools that use or evaluate LLMs and AI agents strongly preferred.

SecureBio aims to effectively secure the world against catastrophic pandemics. They run three projects: SecureDNA, the Nucleic Acid Observatory, and the AIxBio team.