Research Manager, Biological Safety
San Francisco, CA
Posted 12d ago
Remote Work Policy
On-site
Categories
AI Research Engineer
About the job
Anthropic's Safeguards organization is seeking a manager to lead the research engineering team focused on biological safety. This team is responsible for developing evaluations, datasets, and classifiers to govern how AI models handle biological knowledge, ensuring they do not contribute to catastrophic harm. The role involves leading a team of research scientists and engineers in designing and running capability evaluations, curating training data for safety classifiers, and iterating on these classifiers. The manager will set the technical direction, make investment decisions, and own the team's results, while maintaining technical depth to review designs and represent the work to various partners. The core challenge is balancing robust safeguards against sophisticated actors with enabling legitimate researchers in the life sciences.
Responsibilities
- Manage, coach, and grow a team of research scientists and engineers focused on biological safety evaluations and classifiers.
- Set the technical direction and roadmap for biological safety research, and make decisions on team priorities and shipping safeguards.
- Own the quality of capability evaluations for new models in the biological domain and provide deployment recommendations.
- Guide the development of training and evaluation datasets for safety classifiers, incorporating insights from threat modeling experts.
- Oversee the training and iteration of safety classifiers with ML engineers, optimizing for adversarial robustness and low false-positive rates.
- Ensure investment in tooling and pipelines for efficient and repeatable evaluation and classifier development.
- Establish metrics for measuring classifier and evaluation performance against production traffic and prioritize improvements.
- Direct red-teaming and stress-testing of safeguards against evolving threats, models, and product surfaces.
- Partner with Research, Product, Policy, and government affairs to integrate biological safety into model development and act as an escalation point for biological content.
- Represent the team's work in external communications, including model cards, blog posts, and policy documents.
- Track developments in biology, machine learning, and biosecurity for potential risks and mitigations.
Requirements
- Experience managing a technical team, including hiring, coaching, and performance management.
- Proven ability to set technical direction for a team and make prioritization decisions under uncertainty.
- Proficiency in Python with a background in scientific programming and data analysis.
- Solid understanding of ML fundamentals to critically review evaluation design and classifier development.
- Knowledge of modern biology, including high-throughput assays, functional characterization, gene synthesis, genome editing, strain construction, and protein engineering.
- Experience designing quantitative experiments or evaluations and drawing conclusions from noisy results.
- Clear analytical and writing skills, with the ability to explain technical concepts to non-technical stakeholders.
- Familiarity with dual-use research concerns and biosecurity frameworks (e.g., select agent regulations, Biological Weapons Convention, Australia Group guidelines).
- Comfort with ambiguity and shifting priorities.
- Motivation to prevent misuse while enabling beneficial research.