Member of Technical Staff - AI/ML Infrastructure Engineer, RL Post-training
Core
Design, build, and scale compute, scheduling, and data infrastructure to power post-training research on large language models using in-house RL environments.
Role type
Senior ML Infrastructure Engineer (RL Post-training)
Builds
Scalable infrastructure for high-throughput post-training systems and core ML framework primitives
Domain
Artificial Intelligence / Machine Learning Infrastructure / Reinforcement Learning
Deliverable
infrastructure
Required skills
LLM training/inference internals, distributed systems, cloud platforms (AWS, GCP), container orchestration (Kubernetes), data engineering, PyTorch or JAX
Preferred skills
Experience with RL training frameworks (Slime, veRL, Ray Train, SkyRL, Miles), experience building systems from the ground up
Technologies
vLLM, SGLang, Megatron, Ray Train, Slime, veRL, SkyRL, Miles, PyTorch, JAX, Kubernetes, AWS, GCP
Responsibilities
Design and scale compute and data infrastructure for post-training research; Develop and maintain core ML framework primitives and internal tooling; Build evaluation, benchmarking, monitoring, logging, and automated testing systems; Partner with Research Engineers to translate research needs into infrastructure requirements
