英伟达Deep Learning Performance Architect
任职要求
• Masters or PhD or equivalent experience in relevant discipline (CE, CS&E, CS, AI) • SW Agile skills helpful • Excellent C/C++ programming and software design skills • Python experience a plus • Performance modelling, profiling, debug, and code optimization or architectural knowledge of CPU and GPU • GPU programming experience (CUDA or OpenCL) desired • 3+ years of relevant work experience
工作职责
We are now looking for a Deep Learning Performance Software Engineer! We are expanding our research and development for Inference. We seek excellent Software Engineers and Senior Software Engineers to join our team.We specialize in developing GPU-accelerated Deep learning software. Researchers around the world are using NVIDIA GPUs to power a revolution in deep learning, enabling breakthroughs in numerous areas. Join the team that builds software to enable new solutions. Collaborate with the deep learning community to implement the latest algorithms for public release in Tensor-RT. Your ability to work in a fast-paced customer-oriented team is required and excellent communication skills are necessary. What you’ll be doing: • Develop highly optimized deep learning kernels for inference • Do performance optimization, analysis, and tuning • Work with cross-collaborative teams across automotive, image understanding, and speech understanding to develop innovative solutions • Occasionally travel to conferences and customers for technical consultation and training
NVIDIA is developing processors and system architectures that accelerate deep learning on edge devices, workstations and data center GPUs for a variety of applications, including automotive, robotics, large language models (LLMs) and AI generative models. We are looking for an expert deep learning system performance architect to join our modelling, efficiency optimization, performance projections and analysis effort. In this position, you will have the chance to optimize deep learning hardware and software architecture and make the significant impact in a dynamic technology focused company What you’ll be doing :• Analyze performance and efficiency of various machine learning/deep learning algorithms on different architectures • Identify architecture and software performance bottlenecks and propose optimizations • Explore new features and hardware capabilities on deep learning applications
• Analyze state of the art DL networks (LLM etc.), identify and prototype performance opportunities to influence SW and Architecture team for NVIDIA's current and next gen inference products • Develop analytical models for the state of the art deep learning networks and algorithm to innovate processor and system architectures design for performance and efficiency. • Specify hardware/software configurations and metrics to analyze performance, power, and accuracy in existing and future uni-processor and multiprocessor configurations. • Collaborate across the company to guide the direction of next-gen deep learning HW/SW by working with architecture, software, and product teams.
• Design and develop the architecture, interface and features of the GPU kernel library • Keep improving the quality and performance of the library and its GPU kernels • Explore and expand the boundary of innovative technologies like GPU code generation and fusion • Contribute to NVIDIA's AI business by collaborating closely with DL product teams as well as kernel development teams
• Architect Performance Tooling: Develop infrastructure tools/libraries for GPU performance analysis, visualization, and automated workflows used across GPU SW/HW development life cycle. • Unlock Architectural Insights: Analyze GPU workloads to identify bottlenecks and define new hardware profiling features that enhance perf debug and profiling capabilities. • AI-Powered Automation: Build AI/ML-driven tools to automate performance analysis, generate perf optimization guidance, and improve user experience of profiling infrastructure. • Cross-Stack Collaboration: Partner with kernel developers, system software teams, and hardware architects to support performance study, improve CUDA software stack, and co-design performance-centric solutions for current and next-generation GPU architecture