Research Manager, Biological Safety

The posting, as Anthropic wrote it

About Anthropic

Anthropic’s mission is to create reliable, interpretable, and steerable AI systems. We want AI to be safe and beneficial for our users and for society as a whole. Our team is a quickly growing group of committed researchers, engineers, policy experts, and business leaders working together to build beneficial AI systems.

About the role

Anthropic's Safeguards organization builds the policies, evaluations, and enforcement systems that keep our models from contributing to catastrophic harm. We are hiring a manager to lead the research engineering team responsible for biological safety: the evaluations, datasets, and classifiers that govern how our models handle biological knowledge.

You will lead a team of research scientists and engineers who design and run capability evaluations against frontier models, curate training data for our safety classifiers, train and iterate on those classifiers alongside our ML engineers, and measure how they hold up against adversarial pressure in production traffic. You will set the technical direction for that work, decide where the team invests, and own the results.

This is a hands-on management role. Most of your time goes to growing and directing the team, but you will keep enough technical depth to review an eval design, interrogate a classifier's failure modes, and represent the work credibly to Research, Product, and Policy partners.

The core tension your team owns is precision: safeguards need to be robust against sophisticated actors while staying out of the way of the far larger population of legitimate researchers using Claude to accelerate life sciences work. Getting that tradeoff right is an empirical problem, and your team is the one measuring it.

Key responsibilities

Manage, coach, and grow a team of research scientists and engineers working on biological safety evaluations and classifiers, including hiring, onboarding, performance, and career development

Set the technical direction and roadmap for the biological safety research agenda, and make the calls about what the team builds, what it deprioritizes, and when a safeguard is ready to ship

Own the quality of capability evaluations that assess what new models can do in the biological domain, and turn results into deployment recommendations that leadership can act on

Guide the development of training and evaluation datasets for our safety classifiers, working with internal and external threat modeling experts to ground them in realistic risk

Oversee the training and iteration of safety classifiers alongside ML engineers, optimizing jointly for adversarial robustness and low false-positive rates

Ensure the team invests in the tooling and pipelines that make evaluation and classifier development fast and repeatable

Establish how the team measures classifier and eval performance against production traffic, identifies gaps, and prioritizes improvements

Direct red-teaming and stress-testing of safeguards a
[…]
n our team.

Your safety matters to us. To protect yourself from potential scams, remember that Anthropic recruiters only contact you from @anthropic.com email addresses. In some cases, we may partner with vetted recruiting agencies who will identify themselves as working on behalf of Anthropic. Be cautious of emails from other domains. Legitimate Anthropic recruiters will never ask for money, fees, or banking information before your first day. If you're ever unsure about a communication, don't click any links—visit anthropic.com/careers directly for confirmed position openings.

How we're different

We believe that the highest-impact AI research will be big science. At Anthropic we work as a single cohesive team on just a few large-scale research efforts. And we value impact — advancing our long-term goals of steerable, trustworthy AI — rather than work on smaller and more specific puzzles. We view AI research as an empirical science, which has as much in common with physics and biology as with traditional efforts in computer science. We're an extremely collaborative group, and we host frequent research discussions to ensure that we are pursuing the highest-impact work at any given time. As such, we greatly value communication skills.

The easiest way to understand our research directions is to read our recent research. This research continues many of the directions our team worked on prior to Anthropic, including: GPT-3, Circuit-Based Interpretability, Multimodal Neurons, Scaling Laws, AI & Compute, Concrete Problems in AI Safety, and Learning from Human Preferences.

Come work with us!

Anthropic is a public benefit corporation headquartered in San Francisco. We offer competitive compensation and benefits, optional equity donation matching, generous vacation and parental leave, flexible working hours, and a lovely office space in which to collaborate with colleagues. Guidance on Candidates' AI Usage: Learn about our policy for using AI in our application process.