Deep Learning Performance Architect
NVIDIAJob Title
Deep Learning Performance Architect
Role Summary
Work on deep learning performance modeling, analysis, and optimization for inference products focused on large language models (LLMs) and related AI workloads. Influence hardware and software design by identifying performance opportunities and guiding architecture and software teams.
Collaborate with architecture, software, and product teams to specify configurations and metrics that balance performance, power, and accuracy.
Experience Level
Mid-level; requires 3+ years of relevant industry experience.
Responsibilities
Key responsibilities include analyzing workloads, building models, and guiding HW/SW design for performance and efficiency.
- Analyze state-of-the-art deep learning networks (LLMs, AIGC) and identify performance improvement opportunities.
- Prototype performance optimizations and communicate recommendations to software and architecture teams.
- Develop analytical and algorithmic performance models for processors and systems.
- Specify hardware/software configurations and metrics to evaluate performance, power, and accuracy across uni- and multi-processor setups.
- Collaborate cross-functionally to influence next-generation deep learning hardware and software direction.
Requirements
Must-have technical skills and experience. Education requirements are listed separately below.
- 3+ years of relevant work experience in deep learning or systems performance.
- Experience with popular AI models, especially LLMs and AIGC models.
- Familiarity with deep learning frameworks such as PyTorch, JAX, TensorFlow, and TensorRT.
- Knowledge of hardware architectures for deep learning and experience evaluating HW/SW performance trade-offs.
- Strong analytical skills and experience developing performance models and metrics.
- Ability to prototype performance opportunities and work effectively across architecture, software, and product teams.
Education Requirements
BS, MS, or PhD in Computer Science, Electrical Engineering, Mathematics, or a related discipline — 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.
