Lead Inference Engineer (AI)

In short

This role involves building and scaling high-performance AI inference systems, focused on LLM serving (vLLM, SGLang, TensorRT-LLM), GPU performance (CUDA, Triton), and quantization/benchmarking. It requires hands-on technical leadership at a senior/tech lead level, posted by a small, senior, low-bureaucracy team. The position is based in Abu Dhabi, office-based a few times a week, with an initial 3-month remote period before relocation. Advanced English is required.