CUDA Engineer

This is a fully remote position, open to applicants in Uzbekistan.

📋 Description

• Research and enhance LLM inference performance on contemporary GPUs.

• Collaborate with inference and serving frameworks such as vLLM, SGLang, TensorRT-LLM, or comparable systems.

• Examine GPU execution, memory access patterns, kernel performance, and identify inference bottlenecks.

• Create, refine, troubleshoot, or reverse-engineer CUDA kernels and low-level GPU operations.

• Investigate optimization strategies for matrix multiplication, attention mechanisms, and neural network layers.

• Assess performance metrics and discover opportunities to enhance latency, throughput, and GPU utilization.

• Tackle technically demanding challenges at the crossroads of AI systems and high-performance computing.

• Engage in hands-on experimentation and analyze low-level system behavior.

⛳️ Requirements

• Extensive practical experience with CUDA and GPU programming.

• Profound knowledge of GPU architecture, memory hierarchy, parallel execution, and performance enhancement.

• Familiarity with LLM inference, AI systems, GPU kernels, or high-performance computing.

• Knowledge of one or more frameworks such as vLLM, SGLang, TensorRT-LLM, Triton, or FlashAttention.

• Experience in troubleshooting complex performance issues and analyzing low-level system behavior.

• Strong analytical and problem-solving abilities.

• Capability to articulate intricate technical concepts in English.

• A PhD or research experience in Computer Science, Machine Learning, Computer Architecture, or a related discipline (preferred).

• Contributions to publications, research projects, or significant input to open-source GPU/LLM infrastructure (preferred).

• Familiarity with PyTorch internals, distributed inference, quantization, KV cache optimization, or custom GPU kernels (preferred).

• Contributions to repositories like vLLM, SGLang, Triton, FlashAttention, or similar (preferred).

🏝️ Benefits

• Security through thorough client vetting to reduce risks and ensure dependable, timely payments.

• Career support and assistance in exploring new opportunities.

• Legal guidance for independent contractor or sole proprietorship status, tax matters, and associated processes.

• English language courses and opportunities for professional development.

• Team-building activities.

• Flexible working hours.

• 29 days of paid time off (18 working days annually plus all national holidays).

• 10 paid recovery days.

• Comprehensive financial and legal support for independent contractors.

• Complimentary English classes with native speakers or Ukrainian instructors.

• Dedicated HR assistance.

• People-centered management with minimal bureaucracy.

• A welcoming company culture.