AI Safety & Safeguards ML Engineer

anthropic; New York, San Francisco (NY, CA); Hybrid; USD 350,000 - 500,000; Full time

Job summary

An innovative AI company based in New York is looking for ML Engineers and Research Engineers to enhance AI safety through misuse detection systems. Candidates should have at least 4 years of experience, proficiency in Python, and strong communication skills. Responsibilities include developing classifiers, building monitoring systems, and evaluating product safety. The role offers an annual compensation between $350,000 and $500,000, with a requirement for in-office presence at least 25% of the time.

Qualifications

• 4+ years of experience in ML engineering, research engineering, or applied research.
• Experience building ML systems.
• Strong communication skills to explain technical concepts.

Responsibilities

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

Skills

Python

Machine Learning

Communication Skills

Education

Bachelor's degree in a related field

Job description

An innovative AI company based in New York is looking for ML Engineers and Research Engineers to enhance AI safety through misuse detection systems. Candidates should have at least 4 years of experience, proficiency in Python, and strong communication skills. Responsibilities include developing classifiers, building monitoring systems, and evaluating product safety. The role offers an annual compensation between $350,000 and $500,000, with a requirement for in-office presence at least 25% of the time.