Member of Technical Staff - RL Inference
Core
Designing and optimizing low-precision RL training and inference stacks for large-scale distributed systems.
Role type
Member of Technical Staff - RL Inference Engineer
Builds
Inference stack for RL workloads (from ablations to production training runs)
Domain
AI/ML, Reinforcement Learning, Large Language Models
Deliverable
production ML models
Required skills
distributed systems optimization, LLM inference, Python, C++, Rust, PyTorch, Jax, CUDA
Preferred skills
quantization, numerics in LLM inference/training, inference engine development (SGLang, vLLM)
Responsibilities
Design and optimize inference stack for RL workloads; Analyze and address performance bottlenecks in large scale RL systems; Implement novel RL techniques and algorithms with the modelling team
Seniority
Individual Contributor
Sourced via greenhouse · Listed on CareerPlan, which tracks 70,000+ jobs from 20+ sources.