Job Title
Senior GPU Architect, Deep Learning
Role Summary
Design and drive GPU microarchitecture and system-level features that accelerate deep learning workloads. Work within a cross-functional hardware architecture team and collaborate closely with silicon design, firmware, software, and research groups.
Experience Level
Senior β typically requires extensive experience in architecture or accelerator design (commonly 7+ years).
Responsibilities
The role focuses on defining architecture, validating tradeoffs, and guiding implementation for GPU features optimized for deep learning.
- Define microarchitecture and system-level features for GPUs targeting deep learning performance, power, and area trade-offs.
- Perform architectural exploration, modeling, and performance analysis using benchmarks representative of ML/DL workloads.
- Specify hardware blocks and interfaces; drive requirements to RTL, verification, and physical design teams.
- Collaborate with software and compiler teams to ensure efficient mapping of DL operators to hardware.
- Analyze bottlenecks and propose hardware or firmware mitigations to improve throughput and utilization.
- Support silicon bring-up, validation, and performance tuning activities.
- Mentor engineers and contribute to technical roadmaps and cross-team planning.
Requirements
Key technical skills and experience required for success in this role.
- Proven experience in GPU, accelerator, or processor microarchitecture and system design.
- Strong skills in performance modeling, architectural trade-off analysis, and benchmarking for ML/DL workloads.
- Practical familiarity with RTL design/verification flow and the hardware development lifecycle.
- Experience working with software/compilers, and ability to collaborate across HW/SW boundaries.
- Proficiency in scripting and modeling tools (e.g., Python, C/C++) for analysis and prototyping.
- Effective communication and leadership skills to influence cross-functional teams.
- Nice-to-have: prior experience with GPU vendors, deep-learning accelerators, or ML frameworks.
Education Requirements
Not specified.
About the Company
Company: NVIDIA
Headquarters: Santa Clara, California, USA
NVIDIA is a global leader in accelerated computing, renowned for its innovative solutions in AI and digital twins that transform diverse industries. The company specializes in networking technologies, providing end-to-end InfiniBand and Ethernet solutions for servers and storage that optimize performance and scalability. NVIDIA serves sectors such as high-performance computing, enterprise data centers, and cloud computing, constantly reinventing its products and services to stay ahead in the market.

Date Posted: 2026-07-07