CUDA Engineer

About the role

We are seeking a highly technical CUDA Engineer to optimize large language model (LLM) inference on modern GPUs. You will work on cutting‑edge AI systems, diving deep into GPU architecture, low‑level kernels, and performance bottlenecks.

Key responsibilities

• Investigate and optimize LLM inference performance on state‑of‑the‑art GPUs.
• Work with inference and serving frameworks such as vLLM, SGLang, TensorRT‑LLM, or similar.
• 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 opportunities 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 communicate technical concepts in English.

Required skills

• CUDA
• GPU programming
• GPU architecture
• vLLM, SGLang, TensorRT‑LLM, Triton, FlashAttention
• LLM inference optimization
• High‑performance computing

What we offer

• People‑first management with minimal bureaucracy.
• Friendly company culture and flexible working hours.
• 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.