Senior Deep Learning Architect

Details

We are seeking a Senior Deep Learning Architect to help design the next generation of accelerators and system architecture to enable AI performance and efficiency improvements. This role has direct impact on future hardware roadmap and spans hardware, software, research, and production to drive NVIDIA's deep learning platform from silicon to DL frameworks.

Responsibilities

• Understand, analyze, profile, and optimize AI training workloads on state-of-the-art hardware and software platforms.
• Guide development of future generations of artificial intelligence accelerators and systems.
• Develop detailed performance models and simulator infrastructure for computing systems accelerating AI training, and implement and evaluate hardware feature proposals.
• Collaborate across the company to guide the direction of machine learning at NVIDIA; spanning teams from hardware to software and research to production.
• Drive HW/SW co-design of NVIDIA's full deep learning platform stack, from silicon to deep learning frameworks.

Requirements

• PhD in Computer Science, Electrical Engineering, or CSEE with 5+ years of experience; or MS (or equivalent experience) with 8+ years of relevant work experience.
• Strong background in computer architecture, with a proven track record of architecting features in shipping high-performance processors.
• Background in artificial intelligence and large language models, particularly training algorithms and workloads.
• Experience analyzing and tuning application performance on state-of-the-art hardware; performance profiling and tuning of ML workloads.
• Experience with processor- and system-level performance modeling, simulation, and evaluation prior to silicon availability; development of simulator infrastructure.
• Programming skills in C++ and Python.
• Familiarity with GPU computing across all layers of the AI stack, from deep learning frameworks (e.g., PyTorch) down to CUDA.

Benefits

• Base salary range: 224,000 USD - 356,500 USD (final base salary determined by location, experience, and internal pay equity).
• Eligible for equity and benefits (see NVIDIA benefits).
• NVIDIA is an equal opportunity employer committed to diversity and non-discrimination.
• Applications accepted at least until July 29, 2025.

Technologies & Skills Mentioned

C++, Python, GPU computing, PyTorch, CUDA, performance modeling, simulation, AI training workloads, HW/SW co-design, computer architecture, large language models, performance profiling.