CUDA Engineer

This is a fully remote position, open to applicants in Bosnia and Herzegovina.

📋 Description

• Examine 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.

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

• Create, optimize, debug, or reverse-engineer CUDA kernels and low-level GPU operations.

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

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

• Tackle technically challenging issues that demand analytical thinking and practical experimentation.

⛳️ Requirements

• Extensive hands-on experience with CUDA and GPU programming.

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

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

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

• Proven track record in diagnosing complex performance problems and exploring low-level system behavior.

• 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 efforts, 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 similar repositories (preferred).

🏝️ Benefits

• Security through client vetting to reduce risks and ensure reliable, prompt payments.

• Career support and assistance in finding new opportunities if a project isn't a suitable match.

• Legal aid regarding independent contractor or sole proprietorship status, taxes, and related processes.

• English language courses and opportunities for professional development.

• Team-building activities.

• Flexible working hours.

• 29 days of paid time off (18 working days per year 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 support.