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, Dev Tech 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 systems
Build infrastructure or services for profiling data storage, visualization and mining
Work with our users to build / calibrate perf/power models for next generation HW or system
Partner with architects to propose new HW features or improve existing features with real world use cases
What we need to see:
BS+ in Computer Science or related (or equivalent experience) and 5+ years of software development
Strong software design and implementation ability
Strong programming skills with Python, modern C++ or modern web application development
Good understanding in how Deep Learning frameworks works (like Py Torch, Tensor Flow, Megatron-LM and etc...)
Proficient with GIT and P4
Excellent problem solving skills and project management skills
Flexibility for working in an evolving environment with changing requirements
Ways to stand out from the crowd:
Huge plus for experience in building Continuous Profiling system for GPU data center
Skillful in Deep Learning application performance analysis and optimization
Knowledgable in GPU or CPU architecture
Resourceful in GPU application performance or power analysis
Proven experience in contributing to large open source projects
