CUDA / AI Engineer

About the role

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

Key responsibilities

• Investigate and optimise LLM inference performance on modern GPUs.
• Work with inference and serving frameworks such as vLLM, SGLang, TensorRT‑LLM, or similar.
• Analyse GPU execution, memory access patterns, kernel performance and inference bottlenecks.
• Develop, optimise, debug or reverse‑engineer CUDA kernels and low‑level GPU operations.
• Benchmark performance and identify opportunities to improve latency, throughput and GPU utilisation.

Required profile

• Strong hands‑on experience with CUDA and GPU programming.
• Deep understanding of GPU architecture, memory hierarchy and parallel execution.
• Experience with LLM inference, AI systems or high‑performance computing.
• Ability to debug complex performance issues and communicate technical concepts in English.

Required skills

• CUDA
• GPU architecture and performance optimisation
• vLLM, SGLang, TensorRT‑LLM, Triton, FlashAttention
• Python (for AI/ML workflows)
• Debugging low‑level GPU kernels

What we offer

• People‑first management with minimal bureaucracy.
• Flexible working hours and remote‑friendly environment.
• 29 days of PTO plus national holidays and 10 paid recovery days.
• Full financial and legal support for independent contractors.
• Free English classes with native speakers.
• Dedicated HR support.