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
Algorithms @ 4
Deep Learning @ 4
GPU @ 7
HPC
Parallel Programming @ 7
Perl @ 7
Python @ 7
- 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
The NVIDIA GPU Architecture group is seeking a Senior GPU and Deep Learning Architect to lead architecture efforts focused on graphics, parallel computing, and deep learning workloads. The role involves improving GPU architecture for training and inference, developing parallel programming models and new architectures, building simulators, mapping deep learning workloads to current and future hardware, and validating new architectural features. You will collaborate with architects and researchers to advance parallel computing performance and state-of-the-art deep learning systems.
Responsibilities
- Design new hardware features for future processing architectures targeted at deep learning workloads for training and inference.
- Advance the state of parallel computation.
- Evaluate future parallel programming models and their impact on hardware.
- Develop software for hardware simulators, test infrastructures, metrics systems, and databases.
- Collaborate with a team to document, design, develop, analyze, simulate, validate, and verify functional and performance models.
- Develop tests, test plans, and testing infrastructure for new graphics and parallel processing architectures.
- Work with simulators, RTL, and real silicon.
Requirements
- A master's degree in Computer Science, Electrical Engineering, Computer Engineering, or equivalent experience.
- Experience working with hardware targeted at deep learning or mapping deep learning algorithms to hardware.
- At least 8 years of relevant industry experience in GPU or other parallel programming architectures, or equivalent experience.
- Strong programming ability in C, C++, Perl, and Python.
- A background in computer architecture, parallel processing, signal processing, and/or high-performance computing.
- Knowledge of state-of-the-art deep learning algorithms and attention mechanisms is a significant advantage.
- Creative, autonomous, and motivated by challenging technical problems.
Compensation and Benefits
The base salary range is USD 184,000–287,500 for Level 4 and USD 224,000–356,500 for Level 5. Compensation is determined based on location, experience, and the pay of employees in similar positions. The role is also eligible for equity and benefits.
Applications will be accepted at least until January 13, 2026. This posting is for an existing vacancy. NVIDIA uses AI tools in its recruiting processes and is an equal opportunity employer.