Tech Stack
Tag name is followed by "@" symbol and proficiency level value.
About proficiency levels:
- 1-2 — basic awareness. Minimal hands-on experience, and a rudimentary understanding of the technology's purpose;
- 3-6 — daily use. Comfortable and regular usage, capable of handling common tasks and challenges related to the technology;
- 7-9 — you are an expert, you can teach others, you know all the pitfalls and tricks;
- 10 — exceptional knowledge, comprehensive understanding, and adeptness in all aspects of the technology, including advanced problem-solving. Think twice before claiming or demanding such level.
AI @ 6
API @ 4
CUDA @ 4
Communication @ 6
Deep Learning
GPU @ 1
GenAI
Generative AI
HPC
LLVM @ 4
OpenCL @ 4
- 1-2 — basic awareness. Minimal hands-on experience, and a rudimentary understanding of the technology's purpose;
- 3-6 — daily use. Comfortable and regular usage, capable of handling common tasks and challenges related to the technology;
- 7-9 — you are an expert, you can teach others, you know all the pitfalls and tricks;
- 10 — exceptional knowledge, comprehensive understanding, and adeptness in all aspects of the technology, including advanced problem-solving. Think twice before claiming or demanding such level.
Details
NVIDIA is seeking an experienced Systems Software Compiler Engineer to join the PTX (Parallel Thread Execution) Compiler Development team. The role focuses on PTX language design and compiler evolution. PTX enables GPU computing applications including high-performance computing, deep learning, and autonomous driving. It provides a stable programming model and portable instruction set architecture (ISA) for NVIDIA GPUs and is used by compute programming languages compiled to NVIDIA GPUs, as well as by various non-NVIDIA compilers as a compiler target.
The role involves working with NVIDIA GPU Architecture and CUDA Programming Model teams to build abstractions that expose new GPU features in portable and performant ways through the PTX ISA. PTXAS is responsible for implementing the PTX ISA, the PTX compiler front end, optimizer interaction, and runtime aspects involving object files, debug information, linkers, loaders, and the Driver Compiler Interface.
As a senior member of the team, you will lead efforts to enhance PTX Compiler infrastructure to support new compilation models for deep learning and generative AI workloads. You will contribute to evolving the programming model for generative AI and deep learning applications on GPUs.
Responsibilities
- Provide stewardship for the PTX ISA and PTX Compiler infrastructure for generative AI and deep learning.
- Collaborate with architecture and programming model teams to design and implement programming models for next-generation GPUs.
- Work closely with other teams to design compilation stacks and strategies for AI and deep learning workloads.
- Collaborate with teams developing related components to ensure compatibility, robustness, and high-quality code generation.
Requirements
- Bachelor's degree or equivalent experience, master's degree, or Ph.D. in Computer Science, Computer Engineering, or a related field.
- Six or more years of experience with compiler front ends, programming language design, compilers, or linkers.
- Strong analytical and C/C++ programming skills.
- Ability to expertly use AI tools and maintain AI-generated artifacts.
- Experience in at least one area of compiler development, including feature support, code generation, or compiler infrastructure.
- Excellent interactive, verbal, and written communication skills.
- Understanding of a processor ISA; GPU ISA experience is a plus.
- A strong track record of developing, driving, and delivering software products.
Preferred Qualifications
- Experience designing programming languages and drafting programming language standards.
- Knowledge of GPU development and compute APIs such as CUDA and OpenCL.
- Development experience with LLVM IR and MLIR.
Benefits
NVIDIA offers a competitive salary, equity, and a comprehensive benefits package. The company promotes a diverse work environment and is an equal opportunity employer. Applications will be accepted at least until May 3, 2026. This posting is for an existing vacancy. NVIDIA uses AI tools in its recruiting processes.