Share
What you'll be doing:
You will be part of NVIDIA re-targetable GPU compiler backend team
You will contribute to compiler optimizations to produce best-in-class, robust, supportable compiler and tools
Work on challenging problems in register allocation, instruction scheduling, synchronization, loop optimizations etc.
Develop innovative solutions to optimize workloads in Deep Learning, Ray Tracing, HPC etc. by working with industry experts in each field.
Solve unique problems seen only in compiling for massively parallel GPU architecture.
Get a chance to influence and work on new GPU architectures.
What we need to see:
B.S. or higher degree in Computer Science/Engineering
Proficient in compiler design with 5+ years of experience
Strong background in program analysis and high level optimizations
Excellent C and C++ programming skills
Hands on experience in compiler infrastructures like LLVM/GCC
Good understanding of processor architecture
Experience in working in a global team
Self-motivated to get things done
Good communication skills with ability to influence others
Ways to stand out from the crowd:
Masters or PhD preferred, with 8+ years of relevant experience
Demonstrated ability to pursue complex optimization problems
Experience in Scheduling/Register Allocation
Experience in developing CUDA, DirectX, OpenGL/Vulkan applications
These jobs might be a good fit