Software Engineer - Training/Inference (C++)

Highlights

• Build the high-performance platform serving Grok to millions daily.
• Own large-scale model serving systems end-to-end for reliability.
• Your work determines how fast users interact with Grok at scale.

What they offer

• equity
• comprehensive medical, vision, and dental coverage
• 401(k) retirement plan
• short & long-term disability insurance
• life insurance
• discounts and perks

Ideal candidate

Low-level systems builder who thrives on hard performance challenges and ownership. You care about speed, reliability at massive scale and hands-on engineering excellence in a small, driven team.

Requirements

• Deep low-level systems programming (C/C++ or Rust)
• Experience with large-scale, high-concurrent production serving.
• Experience with GPU inference engines (vLLM, SGLang, Triton, TensorRT-LLM, etc.).
• Strong background in system optimizations: batching, caching, load balancing, parallelism.
• Low-level inference optimizations: GPU kernels, code generation.
• Algorithmic inference optimizations: quantization, speculative decoding, distillation, low-precision numerics.
• Experience with testing, benchmarking, and reliability of inference services.
• Experience designing and implementing CI/CD infrastructure for inference.