Build and scale high-performance AI inference with a fast-moving team.

Requirements:

  • Expertise in LLM serving with vLLM, SGLang, or TensorRT-LLM
  • GPU performance skills with CUDA and Triton
  • Knowledge of quantization and benchmarking
  • Hands-on technical leadership
  • Advanced English

Conditions and benefits:

  • Can work remotely for 3 months, with relocation afterward
  • Office-based, a few times per week
  • Competitive salary plus incentives
  • 24 days of annual leave
  • Health insurance
  • Ownership and influence in a small, senior team with low bureaucracy