CUDA / AI Engineer
About The Position
MWDN is seeking a highly technical engineer or researcher with deep expertise in GPU computing, CUDA, and LLM inference optimization. The role focuses on challenging problems at the intersection of AI systems and high-performance computing, including understanding GPU architecture, low-level kernels, LLM inference engines, and performance bottlenecks. The engineer will investigate and optimize LLM inference on modern GPUs and work with inference and serving frameworks such as vLLM, SGLang, TensorRT-LLM, or similar systems. The role also involves analyzing GPU execution and memory access patterns, developing or investigating CUDA kernels and low-level GPU operations, exploring optimizations for matrix multiplication, attention mechanisms, and neural network layers, and benchmarking performance to improve latency, throughput, and GPU utilization. The work requires analytical thinking and hands-on experimentation. MWDN is a global IT outstaffing company with more than 23 years of experience, connecting technology talent with companies across Israel, the USA, Great Britain, and Western Europe. It describes its environment as stable and professional, with client vetting, career support, legal guidance for independent contractors, professional development, English classes, and team-building opportunities.
Requirements
- 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.
- Familiarity with one or more frameworks such as vLLM, SGLang, TensorRT-LLM, Triton, or FlashAttention.
- Experience debugging complex performance issues and investigating low-level system behavior.
- Strong problem-solving skills and the ability to communicate complex technical concepts in English.
Nice To Haves
- PhD or research experience in Computer Science, Machine Learning, Computer Architecture, or a related field.
- Publications, research projects, or meaningful contributions to open-source GPU/LLM infrastructure.
- Experience with PyTorch internals, distributed inference, quantization, KV cache optimization, or custom GPU kernels.
- Contributions to projects such as vLLM, SGLang, Triton, FlashAttention, or related repositories.
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 opportunities to improve latency, throughput, and GPU utilization.
- Work on technically challenging problems requiring analytical thinking and hands-on experimentation.
Benefits
- People-first management with minimal bureaucracy.
- Friendly company culture; employees choose to return.
- Flexible working hours.
- 29 days of PTO (18 working days per year plus all national holidays).
- 10 paid recovery days.
- Full financial and legal support for independent contractors.
- Free English classes with native speakers or Ukrainian teachers.
- Dedicated HR support.
- Career support to help find other opportunities if a project is not the right fit.
- Professional growth opportunities and team-building events.
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
What This Job Offers
Job Type
Full-time
Education Level
No Education Listed
