Security & RL Research Engineer for AI Training Systems

Aicompliance; New York (NY); On-site; USD 320,000 - 405,000; Full time

Job summary

Anthropic is seeking a Security Engineer / Research Engineer, RL Security, to design and operate security controls for reinforcement-learning training systems and review security across the RL stack. The role involves evaluating threats, implementing mitigations, and collaborating with ML research teams to secure AI pipelines across several core environments in the US.

Responsibilities include threat modeling, incident response readiness, and adapting security tooling to evolving RL workloads,

Job description

Anthropic is seeking a Security Engineer / Research Engineer, RL Security, to design and operate security controls for reinforcement-learning training systems and review security across the RL stack. The role involves evaluating threats, implementing mitigations, and collaborating with ML research teams to secure AI pipelines across several core environments in the US.

Responsibilities include threat modeling, incident response readiness, and adapting security tooling to evolving RL workloads,