A key part of NVIDIA's strength is our sophisticated analysis tools that empower NVIDIA engineers to improve perf and power efficiency of our products and the running applications. We are looking for forward-thinking, hard-working, and creative people to join a multifaceted software team with high standards! This software engineering role involves developing analysis tools on various combinations of OS and hardware at different scales from single system to large data center.As a member of the software development team, we will engineer and improve the tools and systems for perf & power verification/analysis/prototyping activities that are carried out internally. We will work with users from different departments like Architecture, Software, DevTech and etc. Our work brings the users intuitive, rich and accurate insight in the workload and the system, and empower them to find opportunities in software and hardware, or build high level models to propose and deliver the best hardware and software to our customers!What you’ll be doing:Build internal perf/power profiling tools for real world application running on NVIDIA products like GPUs or systemsBuild infrastructure or services for profiling data storage, visualization and miningWork with our users to build / calibrate perf/power models for next generation HW or systemPartner with architects to propose new HW features or improve existing features with real world use casesWhat we need to see:BS+ in Computer Science or related (or equivalent experience) and 5+ years of software developmentStrong software design and implementation abilityStrong programming skills with Python, modern C++ or modern web application developmentGood understanding in how Deep Learning frameworks works (like PyTorch, TensorFlow, Megatron-LM and etc...)Proficient with GIT and P4Excellent problem solving skills and project management skillsFlexibility for working in an evolving environment with changing requirementsWays to stand out from the crowd:Huge plus for experience in building Continuous Profiling system for GPU data centerSkillful in Deep Learning application performance analysis and optimizationKnowledgable in GPU or CPU architectureResourceful in GPU application performance or power analysisProven experience in contributing to large open source projects
View Original Job Posting