xAI
Software Engineer, Training/Inference (C++)
$180K–$440K
Palo Alto, CA +2 · Full-time · Posted Oct 4, 2024
- Location
- Palo Alto, CA
Seattle, WA
Palo Alto, CA - Education
- Bachelor’s degree in computer science, computer engineering, or science discipline
About the job
Designs and optimizes large-scale systems that serve Grok, from distributed infrastructure to low-level inference acceleration.
What you'll do
- Build scalable model-serving infrastructure and high-concurrency systems with high reliability.
- Optimize inference latency and throughput, including inference engines and GPU kernels.
- Develop tools and CI/CD infrastructure, and support research on test-time compute, RL rollout, and model-hardware co-design.
What they ask for
- Bachelor’s degree in computer science, computer engineering, or science discipline.
- Low-level system programming experience in C/C++ or Rust.
Nice to have
- Experience with large-scale production serving or GPU inference engines such as vLLM, SGLang, Triton, or TensorRT-LLM.
- Experience with inference optimization, benchmarking, reliability, or CI/CD infrastructure.
Pay
$180,000 - $440,000 USD (base salary)
Tools
C/C++, Rust, GPU kernels, vLLM, SGLang, Triton, TensorRT-LLM, CI/CD
AI focus
Builds and accelerates Grok inference and serving systems, and supports research on test-time compute, RL rollout, and model-hardware co-design.
Model-written summary · the original posting is authoritative