Staff+ Software Engineer, Safeguards Evals

About the role

How do we know whether a model is safe - and how do we know whether the systems we built to catch misuse actually catch it?

Anthropic answers both questions with evaluations. We measure model behavior across misuse, prompt injection, and user well-being to inform training and deployment decisions. We also use AI to investigate potential misuse of Claude, analyzing real-world traffic to surface bad actors and emerging threats that drive enforcement actions. Neither is worth much unless the evaluations behind them are representative, robust, and trustworthy.

This role builds the methods and infrastructure that make them so. Sitting at the intersection of applied ML research and engineering, you'll design experiments to improve how we evaluate both model behavior and the agentic systems that govern it, build datasets that represent real abuse rather than clean approximations of it, and ship those methods into the pipelines that gate model training, agent changes, and launch decisions.

Responsibilities

Evaluation research and methodology. Design and run experiments to improve evaluation quality — developing methods to generate representative test data, simulate realistic user behavior, and validate grading accuracy. Research how different factors (multi-turn conversations, tools, long context, user diversity) impact model safety behavior. Analyze evaluation coverage to identify measurement gaps, and evolve evals so they remain unsaturated and high-signal as model and agent capabilities advance.

Agentic investigation evals. Build and own the evaluation harness for an agentic investigation system — defining metrics, test cases, and grading approaches for a complex, long-horizon agent. Measure agent performance end-to-end (detection precision and recall, investigation quality, robustness) and drive hill-climbing on the hardest harm areas. Construct RL environments to improve Claude's safety investigation capabilities.

Datasets grounded in real harm. Construct high-quality eval datasets representing real-world misuse across harm areas such as cyber attacks, bio weapons, and influence operations, drawing from both real traffic patterns and synthetic generation. Collaborate with Policy and Enforcement to translate observed harm patterns into measurable evaluations.

Productionization and tooling. Ship successful research into evaluation, regression, and release pipelines that run during model training, on every agent change, prompt update, and underlying model upgrade, and beyond launch. Build tooling that enables policy experts to author, run, and iterate on evaluations without engineering support. Surface findings to research and training teams to drive upstream model improvements.

Minimum qualifications

• 8+ years of industry software engineering or ML engineering experience
• Experience building and maintaining data pipelines
• Experience working with LLMs and a working understanding of their capabilities and failure modes — especially agentic systems with tool use and multi-step reasoning
• Strong data analysis skills — you can draw reliable insights from large datasets
• Ability to move fluidly between research prototyping and production-quality code
• Ability to translate ambiguous problems into concrete, testable experiments
• Care deeply about AI safety and want your work to have real impact

Preferred qualifications

• Expertise in building or contributing to LLM or agent evaluation frameworks, benchmarks, or automated grading systems
• Extensive experience in trust and safety, content moderation, or abuse detection systems
• Experience in red teaming, adversarial testing, or jailbreak research on AI systems
• Experience with synthetic data generation or data augmentation
• Experience with distributed systems or large-scale data processing
• Experience with prompt engineering or building LLM-powered applications