Description
NVIDIA is seeking a Senior Deep Learning Software Engineer to join the Algorithmic Model Optimization Team. The team focuses on optimizing generative AI models, such as large language models (LLMs) and diffusion models, for maximal inference efficiency.
As a Senior Deep Learning Software Engineer, you will play a crucial role in developing and scaling up automated inference and deployment solutions. You will work on various aspects of the machine learning stack, including high-level frameworks like PyTorch and HuggingFace, as well as developing and improving high-performance kernel implementations in CUDA, TRT-LLM, and Triton.
Key responsibilities:
- Train, develop, and deploy state-of-the-art generative AI models like LLMs and diffusion models using NVIDIA's AI software stack.
- Leverage and build upon the torch 2.0 ecosystem to analyze and extract standardized model graph representations from arbitrary torch models for automated deployment solutions.
- Develop high-performance optimization techniques for inference, such as automated model sharding techniques, efficient attention kernels with kv-caching, and more.
- Collaborate with teams across NVIDIA to use performant kernel implementations within automated deployment solutions.
- Analyze and profile GPU kernel-level performance to identify hardware and software optimization opportunities.
- Continuously innovate on inference performance to ensure NVIDIA's inference software solutions maintain and increase their leadership in the market.
- Play a pivotal role in architecting and designing a modular and scalable software platform to provide an excellent user experience with broad model support and optimization techniques to increase adoption.
Requirements:
- Master's, PhD, or equivalent experience in Computer Science, AI, Applied Math, or a related field.
- 8+ years of relevant work or research experience in Deep Learning.
- Excellent software design skills, including debugging, performance analysis, and test design.
- Strong proficiency in Python, PyTorch, and related ML tools (e.g., HuggingFace).
- Strong algorithms and programming fundamentals.
- Good written and verbal communication skills and the ability to work independently and collaboratively in a fast-paced environment.
NVIDIA offers highly competitive salaries and a comprehensive benefits package. The base salary range for this position is $184,000 - $287,500 for Level 4 and $224,000 - $356,500 for Level 5.