Senior Deep Learning Algorithm Engineer
Core
Optimize deep learning training and inference workloads on NVIDIA hardware/software platforms to achieve peak performance.
Role type
Senior IC deep learning algorithm engineer (performance optimization)
Builds
Production-quality software and automation tools for NVIDIA's deep learning platform stack
Domain
AI / Deep Learning / GPU Architecture
Deliverable
production ML models
Required skills
Deep learning and neural networks (training & inference), Computer architecture, GPU architecture fundamentals, Application performance analysis and tuning, C++, Python
Preferred skills
Modern LLM inference frameworks (TRT-LLM, vLLM, Ollama), Production deployment of Deep Learning models, Processor and system-level performance modelling, GPU programming (CUDA or OpenCL)
Technologies
CUDA, OpenCL, TRT-LLM, vLLM, Ollama
Responsibilities
Analyze, profile, and optimize deep learning training and inference workloads on state-of-the-art hardware and software platforms, Collaborate with researchers and engineers to improve workload performance, Implement production-quality software across NVIDIA's deep learning platform stack, Build tools to automate workload analysis and optimization workflows
Seniority
Senior, hands-on IC
