Machine Learning Infrastructure Engineer, Safeguards Research

Details

Anthropic’s Safeguards team builds systems that detect and mitigate misuse of AI models, including individual policy violations and sophisticated coordinated attacks. The role focuses on infrastructure for lightweight detection methods trained on model internals and supports research, experimentation, training, evaluation, and production deployment.

The engineer will own the infrastructure that enables researchers to run experiments, train detection methods, and select detections for launch. The work sits between research and production, requiring reliable systems, fast iteration, and trustworthy results as models and workloads evolve.

Responsibilities

• Build and scale the infrastructure and data pipelines behind Safeguards machine learning research.
• Own the training, evaluation, and scoring workflows used by researchers, focusing on reducing the time between an idea and a result.
• Design tooling and interfaces, including libraries and command-line tools, that researchers can use without understanding the underlying systems.
• Build correctness and sanity checks into the technology stack.
• Take high-value research workflows from experiments to reliable, production-grade jobs.
• Improve the throughput, cost, and reliability of large-scale inference and scoring workloads.
• Partner with researchers and engineers across Safeguards to understand current and future workflows.

Requirements

• Strong software engineering fundamentals and hands-on coding ability, with proficiency in Python.
• Experience building and operating data-intensive or distributed systems in production.
• Experience building tooling or infrastructure used as a dependency by engineers or researchers.
• Comfort working across the research-to-deployment pipeline, from exploratory experiments to production systems.
• Ability to debug performance and correctness problems across an unfamiliar stack.
• Strong written and verbal communication skills and a collaborative approach to technical decisions.
• Bachelor’s degree or an equivalent combination of education, training, and experience.
• A field of study relevant to the role, as demonstrated through coursework, training, or professional experience.

Preferred Qualifications

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

Compensation

• Annual salary: $350,000–$500,000 USD.

Work Arrangement

Anthropic currently expects staff to work from one of its offices at least 25% of the time. Some roles may require more office time.

Benefits

Anthropic offers competitive compensation and benefits, optional equity donation matching, generous vacation and parental leave, flexible working hours, and office space for collaboration.