Senior CUDA Engineer for GPU & LLM Inference

MWDN Ltd.; Madrid; On-site; EUR 60,000 - 100,000; Full time

Benefits offered by this job

People-first management

Friendly company culture

Flexible working hours

29 days PTO (18 working days + public)

10 paid recovery days

Support for independent contractors (f

Free English classes

Dedicated HR support

Job summary

MWDN Ltd. is seeking a highly technical engineer or researcher with deep expertise in GPU computing, CUDA, and LLM inference optimization to work on challenging problems at the intersection of AI systems and high‑performance computing.

This opportunity suits someone who enjoys understanding how things work under the hood—from GPU architecture and low‑level kernels to LLM inference engines and performance bottlenecks—and who can contribute across analysis, development, and benchmarking on modern

Qualifications

• Strong hands-on CUDA and GPU programming experience.
• Deep understanding of GPU architecture, memory hierarchy and performance optimization.
• Experience with LLM inference, AI systems, GPU kernels, or HPC environments.
• Familiarity with frameworks such as vLLM, SGLang, TensorRT-LLM, Triton, or FlashAttention.
• Ability to debug complex performance issues and analyze low-level system behavior.
• Excellent problem-solving and English communication skills.

Responsibilities

• Investigate and optimize LLM inference performance on modern GPUs.
• Work with inference frameworks such as vLLM, SGLang, TensorRT-LLM, or similar systems.
• Analyze GPU execution, memory access patterns, kernel performance, and inference bottlenecks.
• Develop, optimize, debug, or reverse-engineer CUDA kernels and low-level GPU operations.
• Explore optimization techniques for matrix multiplication, attention, and neural network layers.
• Benchmark performance and identify opportunities to improve latency, throughput, and GPU utilization.
• Tackle technically challenging problems with strong analytical thinking and hands-on experimentation.

Skills

CUDA programming

GPU architecture

LLM inference

AI systems

Performance optimization

GPU kernel debugging

English communication

Education

PhD in Computer Science / ML / Computer Architecture

MSc in a related field

Tools

vLLM

SGLang

TensorRT-LLM

Triton

FlashAttention

PyTorch internals

Job description

MWDN Ltd. is seeking a highly technical engineer or researcher with deep expertise in GPU computing, CUDA, and LLM inference optimization to work on challenging problems at the intersection of AI systems and high‑performance computing.

This opportunity suits someone who enjoys understanding how things work under the hood—from GPU architecture and low‑level kernels to LLM inference engines and performance bottlenecks—and who can contribute across analysis, development, and benchmarking on modern