CUDA Engineer

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

📋 Description

• Investigate and enhance the performance of LLM inference 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.

• Develop, optimize, troubleshoot, or reverse-engineer CUDA kernels and low-level GPU operations.

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

• Benchmark performance metrics and uncover opportunities to enhance latency, throughput, and GPU utilization.

• Tackle technically demanding challenges that require analytical reasoning and hands-on experimentation.

• Engage in international projects through MWDN, a global IT outstaffing firm that connects tech talent with leading organizations.

⛳️ Requirements

• Strong practical experience in CUDA and GPU programming.

• Comprehensive understanding of GPU architecture, memory hierarchy, parallel execution, and performance optimization techniques.

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

• Familiarity with frameworks like vLLM, SGLang, TensorRT-LLM, Triton, or FlashAttention.

• Proven experience in debugging intricate performance issues and analyzing low-level system operations.

• Excellent problem-solving abilities.

• Capability to articulate complex technical concepts in English.

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

• Publications, research projects, or significant contributions to open-source GPU/LLM infrastructure (preferred).

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

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

🏝️ Benefits

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

• Career support and assistance in locating new projects.

• Legal guidance for independent contractors or sole proprietorship status, taxes, and related procedures.

• English language courses.

• 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.

• Free English classes with native speakers or Ukrainian instructors.

• Dedicated HR support.