> Markdown version of [/jobs/ext/3900855-cuda-ai-performance-engineer-for-llm-inference](https://www.wearedevelopers.com/jobs/ext/3900855-cuda-ai-performance-engineer-for-llm-inference). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# CUDA & AI Performance Engineer for LLM Inference

- **Company:** Mwdn Ltd.
- **Location:** Madrid, Spain
- **Contract:** Permanent contract
- **Skills:** Profiling, Nvidia CUDA, Performance Tuning, Graphics Processing Unit (GPU), High Performance Computing, Large Language Models, Gpu Programming, SGLang, TensorRT, VLLM, Model Inference
- **Published:** October 24, 2026
- **Apply:** https://www.jobleads.com/es/job/cuda-ai-performance-engineer-for-llm-inference--madrid--e03ec16ba598eef5a0ba07ae89466fec9

## About the Role

MWDN Ltd. is seeking a highly technical engineer or researcher with deep expertise in CUDA, GPU programming, and LLM inference optimization to tackle challenging AI system problems and high-performance computing tasks.

Ideal candidates understand GPU architecture from low-level kernels to large-scale inference engines, and enjoy hands-on experimentation, performance profiling, and cross-framework work with vLLM, SGLang, TensorRT-LLM, and related tools.

## Description

MWDN Ltd. is seeking a highly technical engineer or researcher with deep expertise in CUDA, GPU programming, and LLM inference optimization to tackle challenging AI system problems and high-performance computing tasks.

Ideal candidates understand GPU architecture from low-level kernels to large-scale inference engines, and enjoy hands-on experimentation, performance profiling, and cross-framework work with vLLM, SGLang, TensorRT-LLM, and related tools.