Staff Applied Research Engineer
Core
Building tools and research to enable self-improving AI agents to learn from experience autonomously, solving bottlenecks in continuous learning and data efficiency.
Role type
Staff Applied Research Engineer (LLM Post-Training & Agent Learning)
Builds
Serverless RL platform, ART library, RULER reward function, and production-grade training systems for self-improving agents.
Domain
Artificial Intelligence / Machine Learning / Reinforcement Learning
Deliverable
production ML models
Required skills
LLM post-training (SFT, RL, on-policy distillation, reward modeling, policy optimization), distributed training, GPU optimization, CUDA kernel development, experimental design, technical leadership, cross-functional initiative management
Preferred skills
Reinforcement learning research, open source contributions, large-scale model training systems
Technologies
Kubernetes, Megatron, Temporal, Postgres, FastAPI, CUDA
Responsibilities
Generate and investigate research ideas for continuous learning in production, validate research directions across real customer tasks, implement research from hypothesis to production deployment, set technical direction and mentor engineers
Seniority
Staff, hands-on IC with strategic leadership