Senior Deep Learning Software Engineer, Inference and Model Optimization

NVIDIA is an AI computing company developing software and platforms for generative AI and accelerated computing. The Senior Deep Learning Software Engineer will develop and scale automated inference and deployment solutions for large language models and diffusion models, focusing on model optimization, high-performance GPU kernels, and scalable software architecture.

Responsibilities:

• Train, develop, and deploy state-of-the generative AI models like LLMs and diffusion models using NVIDIA's AI software stack
• Leverage and build upon the torch 2.0 ecosystem (TorchDynamo, torch.export, torch.compile, etc...) to analyze and extract standardized model graph representation from arbitrary torch models for our automated deployment solution
• Develop high-performance optimization techniques for inference, such as automated model sharding techniques (e.g. tensor parallelism, sequence parallelism), efficient attention kernels with kv-caching, and more
• Collaborate with teams across NVIDIA to use performant kernel implementations within our automated deployment solution
• Analyze and profile GPU kernel-level performance to identify hardware and software optimization opportunities
• Continuously innovate on the inference performance to ensure NVIDIA's inference software solutions (TRT, TRT-LLM, TRT Model Optimizer) can maintain and increase its 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:

• Masters, PhD, or equivalent experience in Computer Science, AI, Applied Math, or 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
• Contributions to PyTorch, JAX, or other Machine Learning Frameworks
• Knowledge of GPU architecture and compilation stack, and capability of understanding and debugging end-to-end performance
• Familiarity with NVIDIA's deep learning SDKs such as TensorRT
• Prior experience in writing high-performance GPU kernels for machine learning workloads in frameworks such as CUDA, CUTLASS, or Triton