
CUDA Engineer
Posted Oct 21

Posted Oct 21
This is a fully remote position, open to applicants in Serbia.
• Conduct investigations and enhancements on LLM inference performance utilizing modern GPUs.
• Collaborate with inference and serving frameworks such as vLLM, SGLang, TensorRT-LLM, or other comparable systems.
• Examine GPU execution, memory access patterns, kernel performance, and identify inference bottlenecks.
• Design, enhance, debug, or reverse-engineer CUDA kernels and low-level GPU operations.
• Investigate optimization strategies for matrix multiplication, attention mechanisms, and layers of neural networks.
• Perform benchmarking to assess performance and discover areas for improving latency, throughput, and GPU utilization.
• Tackle technically demanding challenges that require analytical thinking and hands-on experimentation.
• Extensive hands-on experience with CUDA and GPU programming.
• Profound understanding of GPU architecture, memory hierarchy, parallel execution, and performance optimization techniques.
• Background in LLM inference, AI systems, GPU kernels, or high-performance computing.
• Familiarity with frameworks such as vLLM, SGLang, TensorRT-LLM, Triton, or FlashAttention.
• Proven experience in debugging intricate performance issues and analyzing low-level system behavior.
• Strong problem-solving capabilities.
• Proficient communication of complex technical concepts in English.
• A PhD or research experience in Computer Science, Machine Learning, Computer Architecture, or a related discipline is preferred.
• Publications, research initiatives, or significant contributions to open-source GPU/LLM infrastructure are advantageous.
• Experience with PyTorch internals, distributed inference, quantization, KV cache optimization, or custom GPU kernels is a plus.
• Contributions to vLLM, SGLang, Triton, FlashAttention, or related repositories are beneficial.
• Security through client vetting to reduce risks and ensure reliability and timely payments.
• Career support and assistance in finding new project opportunities.
• Legal assistance regarding independent contractor or sole proprietorship status, taxes, and related processes.
• English language courses.
• Opportunities for professional growth.
• Team-building events.
• Flexible working hours.
• 29 days of PTO (18 working days per year plus all national holidays).
• 10 paid recovery days.
• Comprehensive financial and legal support for independent contractors.
• Free English classes with native speakers or Ukrainian instructors.
• Dedicated HR support.
Sargent & Lundy
Willow Innovations, Inc.
Astrolab
Get handpicked remote jobs straight to your inbox weekly.