jobs

ML/Research Engineer, Safeguards

Anthropic is hiring an ML/Research Engineer for its Safeguards ML team in San Francisco or New York City. The team builds systems that detect and mitigate misuse of AI, protect user wellbeing, and help ensure that models behave appropriatel

Company

Anthropic

Location

San Francisco, CA, United States; New York City, NY, United States

Status

Closed

Posted

2026-09-13T13:32:19.422+00:00

Anthropic's Safeguards ML team is hiring an ML/Research Engineer in San Francisco or New York, hybrid. The role builds classifiers that flag misuse and anomalous behavior, synthetic-data pipelines for training them, and automated ways to source evaluations. It also covers monitoring harms that unfold across multiple exchanges, such as coordinated cyber attacks and influence operations, and testing agentic products: threat models, test environments, prompt-injection defenses, and automated red-teaming. The posting asks for at least four years in ML engineering, research engineering or applied research, plus Python and machine-learning systems experience.