Research Scientist/Engineer, Biological Safety

Sourced from aihiringboard.com

Anthropic is seeking a Research Scientist/Engineer focused on Biological Safety to build the safety and oversight mechanisms governing how its frontier models handle biological knowledge. You will design and run capability evaluations, curate training data for safety classifiers, and stress-test safeguards against adversarial pressure in production. The role sits at the intersection of applied ML and biosecurity, translating threat models into evals, datasets, and deployed systems while balancing robustness against low false-positive rates for legitimate life sciences researchers.

• Design, build, and run capability evaluations assessing what new models can do in the biological domain and turn results into deployment recommendations
• Develop training and evaluation datasets for safety classifiers, grounded in realistic risk with threat modeling experts
• Train, tune, and iterate on safety classifiers with ML engineers, optimizing for adversarial robustness and low false-positive rates
• Build tooling and pipelines that make evaluation and classifier development fast and repeatable
• Analyze classifier and eval performance against production traffic, identify gaps, and prioritize improvements
• Design and run red-teaming and stress-testing of safeguards as threats, models, and product surfaces evolve
• Partner with Research, Product, and Policy teams to embed biological safety throughout the model development lifecycle