Senior Machine Learning Engineer

Lead the design and implementation of high-performance inference systems for large language models (LLMs). You will architect, develop, and optimize advanced LLM inference algorithms and GPU kernels, focusing on improving latency, throughput, and cost efficiency. This role involves deep performance profiling, contributing to open-source ML infrastructure, and staying at the forefront of LLM serving research.

• Design and implement high-performance Python, C++, CUDA, and Triton code for LLM inference
• Architect and optimize LLM inference algorithms (quantization, sparsity, attention, etc.)
• Drive deep performance profiling and benchmarking on NVIDIA GPUs
• Own end-to-end optimization of vLLM-based inference pipelines
• Contribute to and maintain upstream open-source ML infrastructure (vLLM)
• Evaluate and integrate state-of-the-art LLM serving techniques