Machine Learning Infrastructure Engineer, Safeguards Research

Anthropic's Safeguards team builds systems to detect and mitigate misuse of AI models. This role owns the infrastructure behind machine learning research for safeguards, building tooling, pipelines, and systems that researchers rely on.

• Build and scale infrastructure and data pipelines for Safeguards ML research.
• Own training, evaluation, and scoring workflows, reducing time from idea to result.
• Design tooling and interfaces (libraries, CLI tools) for researchers.
• Build correctness and sanity checking into the stack.
• Take research workflows to production-grade jobs.
• Improve throughput, cost, and reliability of large-scale inference and scoring.
• Partner with researchers and engineers to anticipate needs.

• Strong software engineering fundamentals and proficiency in Python.
• Experience building and operating data-intensive or distributed systems in production.
• Experience building tooling or infrastructure used by other engineers or researchers.
• Comfort across research-to-deployment pipeline.
• Ability to debug performance and correctness problems.
• Strong communication and collaboration.

• Experience with high-performance, large-scale ML systems.
• Familiarity with language modeling and transformers, including model internals.
• Experience with ML framework internals, GPU/accelerator programming, or inference optimization.
• Experience with experiment tracking, caching layers, or evaluation harnesses.
• Experience with probes, interpretability, or classifier development.
• Interest in AI misuse risks.

Annual salary: $350,000—$500,000 USD.

Bachelor's degree or equivalent. Hybrid policy: at least 25% in office. Visa sponsorship available.