Lead AI Systems & Inference Engineer

### About OpenAI OpenAI's mission is to ensure that artificial general intelligence benefits all of humanity. ### The Role We are seeking an experienced **AI Systems Engineer** to optimize our global model inference clusters serving billions of token requests daily. #### Responsibilities: - Optimize custom CUDA kernels, tensor parallel distribution, and KV cache compaction. - Build resilient routing layers capable of handling massive query volume spikes. - Profile and shave microseconds off latency across LLM decoding loops. #### Requirements: - Deep expertise in GPU architectures, PyTorch, C++, and low-level CUDA programming. - Experience serving frontier LLMs at scale with Triton, vLLM, or TensorRT-LLM.