GPU Profiling Software Engineer
Core
Developing software libraries and performance analysis tools for NVIDIA GPUs to help developers debug, profile, and optimize applications at datacenter scale.
Role type
System software engineer (GPU profiling and performance analysis)
Builds
GPU profiling libraries, performance analysis tools, and low-level libraries for accelerated computing
Domain
High Performance Computing, Deep Learning, GPU Architecture
Deliverable
production ML models | product features
Required skills
C, C++, Python, Data Structures and Algorithms, Computer Architecture (x86, ARM, GPUs), Operating System concepts, SW design principles
Preferred skills
Device Drivers or System Software development, GPU APIs (CUDA, OpenCL, OpenGL, Direct3D, Vulkan), authoring developer tools for GPUs, performance analysis of GPU applications, Assembly language for multi-processor architectures
Technologies
CUDA, OpenCL, OpenGL, Direct3D, Vulkan, Nsight tools
Responsibilities
Design, implement, and verify performance metrics for NVIDIA GPUs; develop methodologies for profiling data collection from GPUs; define and improve GPU profiling library features; read HW specs to design solutions; craft software unit tests and frameworks; support platforms from super-computers to embedded systems
Seniority
Mid-Senior, hands-on IC
