Senior AI Engineer
Core
Build adversarial RL environments and evaluation systems to test and train frontier AI agents.
Role type
Senior AI Engineer (RL Infrastructure & Evaluation)
Builds
Adversarial RL environments, verifiers, and task evaluation engines for frontier model labs
Domain
AI Safety, Reinforcement Learning, Cloud Infrastructure
Deliverable
production ML models
Required skills
Python, Docker, Kubernetes, cloud infrastructure, distributed systems, message queues, system design, autonomous problem solving
Preferred skills
AI/ML academic background, LLM/agent engineering, post-training/RL fine-tuning, security/red teaming
Technologies
Python, Docker, Kubernetes, AWS
Responsibilities
Build end-to-end RL environments including replica systems, planted attacks, and verifiers; Design and maintain task evaluation engines for frontier labs; Scale run pipelines on Kubernetes with sandboxed runners; Collaborate with researchers to iterate environments based on post-training results; Review designs and code to raise engineering standards
