Anthropic is building reliable, interpretable, and steerable AI systems. The role focuses on evaluating the safety systems that detect misuse of Claude. You will design experiments, build an evaluation harness, create datasets that represent real-world misuse, measure agent performance, and productionize research into pipelines that gate system changes. This work directly informs enforcement actions and model launch decisions to ensure trust in automated abuse detection.
Staff+ Software Engineer, Safeguards Evals na Anthropic
Híbrido - San Francisco, CA; New York City, NY; Seattle, WA
Ver mais vagas na AnthropicSalary
R$ 320,000 - 485,000
Requirements
Skills
- Proficiency in Python and comfort working across the stack
- 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
- 8+ years of industry software engineering experience
- Expertise in building or contributing to 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
Responsibilities
- Build and own the evaluation harness for an agentic investigation system — defining metrics, test cases and grading approaches for a complex long horizon agent
- Construct high-quality eval datasets representing real-world misuse across harm areas (e.g., cyber attacks, bio weapons, influence operations), drawing from real traffic patterns and synthetic generation
- Measure agent performance end-to-end (detection precision/recall, investigation quality, robustness) and drive hill-climbing on the hardest harm areas
- Analyze coverage to identify measurement gaps, and evolve evals so they remain unsaturated and high-signal as agent capabilities advance
- Productionize successful research into regression and release pipelines that run on every agent change, prompt update, and underlying model upgrade
- Build tooling that enables policy experts to author, run, and iterate on evaluations without engineering support
- Construct RL environments to improve Claude’s safety investigation capabilities
Technologies
PythonLLMsData pipelinesDistributed systemsLarge-scale data processingPrompt engineeringLLM-powered applications
Descubra se seu currículo está pronto para esta vaga
Veja como nossa IA pode otimizar seu currículo e aumentar suas chances de conseguir esta posição.