Staff+ Software Engineer, Safeguards Evals

Menlo Ventures; New York (NY); On-site; USD 320,000 - 485,000; Full time

Job summary

Anthropic is seeking an experienced engineer to build evaluation infrastructure for its safety and abuse-detection systems. You will design experiments, build datasets from real-world traffic, and ship evaluation methods into pipelines that gate changes to Claude's safety stack.

You will work at the intersection of ML research and engineering, applying tests across harm areas, measuring detection and investigation quality, and contributing to robust, trustworthy AI systems.

Qualifications

• Proficiency in Python and data pipelines experience.
• Experience with LLMs and agentic systems, including multi-step reasoning.
• Strong data analysis skills and the ability to draw reliable insights from large datasets.
• Ability to move fluidly between research prototypes and production-grade code.
• Translate ambiguous problems into concrete, testable experiments.

Responsibilities

• Build and own the evaluation harness for an agentic investigation system, defining metrics and tests.
• Construct datasets representing real-world misuse across harm areas.
• Measure agent performance end-to-end and drive improvements in hard harm areas.
• Analyze coverage to close measurement gaps and keep evals high-signal.
• Productionize research into regression and release pipelines for every agent change.
• Build tooling for policy experts to author, run, and iterate evaluations without heavy engineering support.
• Construct RL environments to improve Claude’s safety investigation capabilities.

Skills

Python

Data analysis

LLMs & agentic systems

Production-quality code

Experiment design

Cross-stack development

Education

Bachelor's degree

Tools

LLMs

Prompt engineering

Distributed systems

Data processing frameworks

Job description

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

How do we know our safety systems actually catch misuse? Anthropic increasingly uses AI to investigate potential misuse of Claude — analyzing real‑world traffic to surface bad actors, policy violations, and emerging threats. Its findings inform enforcement actions and model launch decisions, which means we need rigorous, trustworthy answers to questions such as: “Does the monitoring agent catch what it should?” “Where does it fail?” “Does it stay reliable as adversaries adapt, as models improve, and as the agent itself changes?”

This role builds the evaluation infrastructure that answers those questions. You’ll sit at the intersection of applied ML research and engineering — designing experiments to measure how well an investigative agent performs across harm areas, building datasets that represent real abuse rather than synthetic benchmarks, and shipping those methods into pipelines that gate every change to the system. Your work directly determines how much trust Anthropic can place in its automated abuse detection, and where we invest to make it better.

Key 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 evaluation 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.

Minimum Qualifications

• 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.

Preferred Qualifications

• 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.

Compensation

Annual Salary: $320,000 – $485,000 USD

Logistics

• Minimum education: Bachelor’s degree or an equivalent combination of education, training, and/or experience.
• Required field of study: A field relevant to the role as demonstrated through coursework, training, or professional experience.
• Minimum years of experience: Years of experience required will correlate with the internal job level requirements for the position.
• Location‑based hybrid policy: We expect all staff to be in one of our offices at least 25% of the time. However, some roles may require more time in our offices.
• Visa sponsorship: We sponsor visas for this role and will make every reasonable effort to obtain a visa if an offer is made.