ML/Research Engineer, Safeguards
Core
Build ML systems to detect and mitigate misuse of AI systems, including policy violations, coordinated attacks, and prompt injection, while developing defenses and threat models.
Role type
Senior ML/Research Engineer (AI Safety)
Builds
Production classifiers, monitoring systems for harms, and automated red-teaming environments for agentic products.
Domain
AI Safety / Machine Learning
Deliverable
production ML models
Required skills
Python, building ML systems, research-to-deployment pipeline, developing classifiers, anomaly detection, adversarial robustness, red-teaming
Preferred skills
language modeling and transformers, behavioral ML, interpretability, reinforcement learning, high-performance large-scale ML systems
Responsibilities
Develop classifiers to detect misuse and anomalous behavior at scale; 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
Seniority
Senior, hands-on IC