ML/Research Engineer, Safeguards

Anthropic is looking for ML and Research Engineers to detect and mitigate misuse of AI systems. You will build classifiers, monitor for coordinated attacks, and develop defenses. Requires 4+ years of ML engineering experience and Python proficiency.

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

• 4+ years of experience in ML engineering or applied research. Proficiency in Python. Comfortable working from research to deployment. Strong communication skills.

• Experience with language modeling and transformers, building classifiers, anomaly detection, adversarial machine learning, interpretability, reinforcement learning, large-scale ML systems.