Senior Machine Learning Engineer
Core
Architect, develop, and optimize high-performance LLM inference systems, GPU kernels, and numerical computing components for production-scale serving environments.
Role type
Senior IC machine learning engineer (LLM inference systems)
Builds
vLLM-based inference pipelines, GPU kernels, and distributed serving systems
Domain
Large Language Models (LLM) / High-Performance Computing (HPC)
Deliverable
production ML models
Required skills
High-performance Python, Modern C++, CUDA, Triton, GPU memory architecture, LLM inference optimization, distributed computing, performance profiling
Preferred skills
Open-source contribution, AI-assisted development, emerging serving techniques
Technologies
vLLM, PyTorch, Nsight Systems, Nsight Compute, CUPTI, CUTLASS, NVIDIA GPUs
Responsibilities
Architect and optimize LLM inference algorithms (quantization, sparsification, speculative decoding); Drive deep performance profiling and benchmarking on NVIDIA GPUs; Own end-to-end optimization of inference pipelines; Evaluate and integrate state-of-the-art serving techniques; Set engineering standards and conduct peer reviews; Contribute to upstream open-source vLLM maintenance
Seniority
Senior, hands-on IC
