Senior Deep Learning Performance Architect
NVIDIAJob Title
Senior Deep Learning Performance Architect
Role Summary
Senior engineer responsible for performance analysis, modeling, and architecture development for deep learning and high-performance computing systems. Work with hardware and software teams to shape future GPU/ASIC features and system-level trade-offs.
Primary focus: evaluate performance, power, and area (PPA), build analytical models and simulators, and guide HW/SW co-design for large-scale training and inference.
Experience Level
Senior — requires 6+ years of relevant experience in performance analysis or architecture for AI/Deep Learning systems.
Responsibilities
Key responsibilities include:
- Develop new architectures and optimizations to improve deep learning performance and efficiency.
- Analyze performance, cost, and power trade-offs using analytical models, simulators, and test suites.
- Evaluate system- and feature-level PPA and run architecture simulations (C++/Python).
- Study hardware/software interactions and their impact on algorithms, programming models, and applications.
- Collaborate with software, product, and research teams to influence HW and SW direction for DL.
Requirements
Must-have qualifications and skills:
- 6+ years of relevant experience in GPU or deep-learning ASIC architecture for distributed training and/or inference across multi-chip or multi-node systems.
- Experience with performance modeling, architecture simulation, profiling, and performance analysis.
- Solid foundation in machine learning and deep learning, including understanding transformer-based architectures at scale.
- Strong programming skills in Python, C, and C++.
Nice-to-have:
- Experience with DNN training/inference and optimizations in frameworks such as PyTorch, JAX, or TensorRT.
- Familiarity with SW/HW co-design and advanced optimizations for LLM training and inference.
- Experience applying AI to accelerate software engineering workflows.
- Demonstrated self-motivation, creative and critical thinking.
Education Requirements
MS or PhD in Computer Science, Computer Engineering, Electrical Engineering, or equivalent practical experience.
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.
