CUDA Engineer – LLM Inference Optimization

About the role

MWDN, a global IT outstaffing company, is looking for a highly technical engineer or researcher with deep expertise in GPU computing, CUDA and LLM inference optimization. The role works on challenging problems at the intersection of AI systems and high-performance computing, from GPU architecture and low-level kernels to inference engines and performance bottlenecks.

Key responsibilities

• Investigate and optimize LLM inference performance on modern GPUs.
• Work with inference and serving 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 mechanisms and neural network layers.
• Benchmark performance and identify ways to improve latency, throughput and GPU utilization.

Required profile

• Strong hands-on experience with CUDA and GPU programming.
• Deep understanding of GPU architecture, memory hierarchy, parallel execution and performance optimization.
• Experience with LLM inference, AI systems, GPU kernels or high-performance computing.
• Ability to debug complex performance issues and investigate low-level system behavior.
• Nice to have: PhD or research experience in CS, ML or computer architecture; publications or open-source contributions to GPU/LLM infrastructure; experience with PyTorch internals, distributed inference, quantization, KV cache optimization or custom GPU kernels.

Required skills

• CUDA and GPU programming
• One or more frameworks such as vLLM, SGLang, TensorRT-LLM, Triton or FlashAttention
• Ability to explain complex technical concepts in English

What we offer

• Flexible working hours and 29 days of PTO (18 working days plus national holidays)
• 10 paid recovery days
• Full financial and legal support for independent contractors
• English classes and professional development, plus team-building events
• Support for finding new projects and guidance on legal matters