LEAD INFERENCE ENGINEER
JAYA TALENTAbu DhabiГибрид
AILLMGPUCUDAInferenceSGLangTensorRT-LLMBenchmarkingQuantization
Описание
Build and scale high-performance AI inference with a sharp, fast-moving team!
Requirements
- LLM serving pro (vLLM / SGLang / TensorRT-LLM)
- GPU performance skills (CUDA / Triton)
- Quantization & benchmarking know-how
- Hands-on technical leadership
- Advanced English
We offer
- Competitive salary + incentives
- 24 days annual leave
- Health insurance
- Real ownership & influence
- Small, senior team, low bureaucracy
Hiring process
- Apply via link: [•••]