AI Safety & Misuse Detection Engineer

Anthropic; New York (NY); Hybrid; USD 350,000 - 500,000; Full time

Job summary

Anthropic in New York is seeking ML Engineers and Research Engineers to detect and mitigate misuse of AI systems. You will build classifiers and systems to monitor and improve safety. The role requires at least 4 years of relevant experience, proficiency in Python, and strong communication skills. Compensation ranges from $350,000 to $500,000 annually with a hybrid work policy requiring some office presence.

Qualifications

• 4+ years of experience in ML engineering, research engineering, or applied research.
• Comfortable working across the research-to-deployment pipeline.
• Concerned about misuse risks of AI systems.

Responsibilities

• Develop classifiers to detect misuse and anomalous behavior.
• Build systems to monitor for harms across exchanges.
• Evaluate and improve the safety of agentic products.
• Conduct research on automated red-teaming.

Skills

Proficiency in Python

Experience building ML systems

Strong communication skills

Education

Bachelor’s degree or equivalent

Job description

Anthropic in New York is seeking ML Engineers and Research Engineers to detect and mitigate misuse of AI systems. You will build classifiers and systems to monitor and improve safety. The role requires at least 4 years of relevant experience, proficiency in Python, and strong communication skills. Compensation ranges from $350,000 to $500,000 annually with a hybrid work policy requiring some office presence.