jobs
Senior Deep Learning Software Engineer, Inference and Model Optimization
NVIDIA is at the forefront of the generative AI revolution! The Algorithmic Model Optimization Team specifically focuses on optimizing generative AI models such as large language models (LLM) and…
- Company
- NVIDIA
- Location
- US, CA, Santa Clara; US, Remote
- Status
- Closed
- Posted
- 2026-10-30
NVIDIA's Algorithmic Model Optimization Team is hiring a senior software engineer to build and scale automated inference and deployment software, including the TensorRT Model Optimizer. The work covers the torch 2.0 ecosystem (TorchDynamo, torch.export, torch.compile), automated sharding such as tensor and sequence parallelism, attention kernels with KV caching, and GPU kernel profiling. The posting asks for a master's or PhD or equivalent, eight or more years in deep learning, and strong Python and PyTorch skills. Salary bands are published for two levels.
Original job posting