Skip to content
AI.info

jobs

Software Engineer, Training/Inference (C++)

SpaceX was founded under the belief that a future where humanity is out exploring the stars is fundamentally more exciting than one where we are not. Today, SpaceX is actively developing the…

Company
xAI
Location
Palo Alto, CA; Seattle, WA
Status
Open
Posted
2024-10-05 00:14 UTC

xAI is hiring a software engineer for its inference team in Palo Alto, on-site, to build the platform serving the Grok model to millions of users. The work spans distributed serving infrastructure — global KV cache, continuous batching, load balancing, auto-scaling — plus GPU kernel work, quantization, speculative decoding, latency and throughput tuning, and CI/CD for endpoint deployment. The posting asks for deep C/C++ or Rust systems programming, large-scale production serving, and experience with inference engines including vLLM, SGLang, Triton or TensorRT-LLM. Base pay is listed at $180,000–$440,000.

Original job posting