### Summary Description
Join NVIDIA as a Senior LLM Performance Engineer, where you will play a pivotal role in enhancing the performance of Large Language Model (LLM) training. This position requires a passion for performance analysis and optimization and the ability to work across various layers of the hardware and software stack. From GPU architecture to deep learning frameworks, your expertise will help them achieve peak performance in one of the most crucial AI workloads today. You'll have the chance to influence both the hardware and software roadmap at a leading tech company that is setting the stage for the AI revolution, enabling deep learning users globally to experience accelerated training capabilities.
### Compensation and Benefits
- **Base Salary**: $180,000 - $339,250, with determination based on location, experience, and peer salaries.
- **Equity Options**: Eligibility for equity as part of the compensation package.
- **Comprehensive Benefits**: Access to a robust benefits package that includes health, wellness, retirement plans, and more. Details can be found at [NVIDIA Benefits](https://www.nvidia.com/en-us/benefits/).
### Why You Should Apply for This Position Today
- Be part of a fast-growing company recognized as a leader in AI technology.
- Work with some of the most brilliant minds in the industry on cutting-edge projects that directly impact the future of AI.
- Opportunities for both professional and personal growth in an inclusive and diverse work environment.
- Contribute to significant advancements in deep learning and AI, shaping the future of intelligent technology.
- Experience shared success and dynamism as NVIDIA continues to lead the charge in groundbreaking AI applications.
### Skills
- **Performance Analysis**: Expertise in understanding and optimizing performance metrics across complex systems.
- **Deep Learning Proficiency**: Strong background in deep learning, specifically in training and large language models.
- **Computer Architecture Knowledge**: Deep understanding of computer architecture principles, particularly GPU architecture.
- **Application Performance Tuning**: Proven experience in analyzing and tuning application performance, ideally within GPU environments.
- **Programming Languages**: Proficient in C++, Python, and CUDA for software development and optimization.
- **Familiarity with Deep Learning Frameworks**: Working knowledge of popular frameworks such as PyTorch and JAX.
- **Performance Modeling**: Experience with processor and system-level performance modeling.
### Responsibilities
- Analyze, profile, and optimize LLM training on cutting-edge hardware and software platforms.
- Address performance issues across various LLM types, encompassing both research and industry applications.
- Develop production-quality software across NVIDIA’s deep learning platform stack, including drivers and framework layers.
- Simulate key LLM workload behaviors within NVIDIA’s proprietary simulation tools to aid future architecture analysis.
- Create tools that streamline workload analysis and optimization processes to enhance overall workflow efficiency.
### Qualifications
- **Education**: PhD (or equivalent experience) in Computer Science, Electrical Engineering, or Computer Engineering with 5+ years of experience; or a Master's degree with 8+ years of relevant experience.
- **Deep Learning Expertise**: In-depth understanding of neural networks and practical experience with large language models.
- **Computer Architecture Acumen**: Familiarity with GPU fundamentals and insights into performance tuning.
- **Analytical Skills**: Strong experience in profiling, analyzing, and enhancing application performance.
### Similar Occupations / Job Titles that Would Be a Great Fit for This Role
- AI Performance Optimization Engineer
- Deep Learning Engineer
- GPU Architect
- Software Engineer - AI Systems
- Machine Learning Systems Engineer
- Data Scientist focused on AI Performance
- Research Scientist - AI Optimization
### Education Requirements
- **Degree Category**: PhD or Master's in Computer Science, Electrical Engineering, or Computer Engineering.
### Education Requirements Credential Category
- **Advanced Degree**: Completion of a doctoral program or a Master’s degree relevant to computer science or engineering disciplines.
### Experience Requirements
- Minimum of 5 years of experience (with a PhD) or 8 years of experience (with a Master's) in roles involving performance analysis and optimization, deep learning, neural networks, and project contributions at a high technical level.
### Why Work in Santa Clara, CA?
Santa Clara, CA offers an exhilarating environment for tech professionals. Nestled in the heart of Silicon Valley, the region is renowned for its vibrant tech ecosystem filled with innovation, diversity, and growth opportunities. Home to numerous tech giants and startups alike, Santa Clara provides a collaborative atmosphere with access to cutting-edge dev
Location: Santa Clara, CA
Posted: Aug. 25, 2024, 4:06 a.m.
Apply Now Company Website