Palk täpsustamataTuruvahemik: 4150–5750 €
Responsibilities
Optimizing LLM inference performance on modern GPUs and working with inference and serving frameworks such as vLLM, SGLang, and TensorRT-LLM. The work also involves analyzing GPU execution and memory bottlenecks, developing and debugging CUDA kernels, and benchmarking latency, throughput, and GPU utilization.
Requirements
- CUDA
- GPU programming
- GPU architecture
- LLM inference
- vLLM
- TensorRT-LLM
- Triton
- Performance debugging
- English communication
- PhD or research experience
Employer offers
- English courses
- Legal assistance
- HR support
- Flexible working hours
- 29 days PTO
- 10 paid recovery days
- Career support