CUDA / AI Engineer
Core
Optimize LLM inference performance on modern GPUs by developing and debugging low-level CUDA kernels and analyzing GPU execution patterns.
Role type
Senior IC CUDA / AI Engineer (LLM inference optimization)
Builds
High-performance LLM inference engines and serving frameworks
Domain
Artificial Intelligence / High-Performance Computing
Deliverable
production ML models
Required skills
CUDA programming, GPU architecture, LLM inference optimization, kernel debugging, performance benchmarking, matrix multiplication optimization, attention mechanism optimization, memory hierarchy management, parallel execution, Triton, FlashAttention, vLLM, SGLang, TensorRT-LLM
Preferred skills
PyTorch internals, distributed inference, quantization, KV cache optimization, open-source contributions to GPU/LLM infrastructure, PhD in Computer Science or related field