jobs

Member of Technical Staff - RL Inference

SpaceXAI’s mission is to create AI systems that can accurately understand the universe and aid humanity in its pursuit of knowledge. Our team is small, highly motivated, and focused on engineering excellence. This organization is for indivi

Company

xAI

Location

Palo Alto, CA

Status

Open

Posted

2026-07-06T14:59:58+00:00

An engineer joins xAI's RL infrastructure team to work on low-precision reinforcement learning training and inference. The work covers designing and optimizing the inference stack across RL workloads, from small ablations to full production training runs, profiling and fixing performance bottlenecks in large-scale RL systems, and implementing new RL techniques alongside the modelling team. The posting asks for experience with large-scale distributed systems and LLM inference, proficiency in Python, C++, Rust, PyTorch, JAX or CUDA, and preferred knowledge of quantization, numerics, and engines such as SGLang or vLLM.