Job Description
Senior deep learning engineer role focused on optimizing and deploying diffusion and vision-language models for visual generative AI on NVIDIA GPU platforms. The team builds high‑performance inference paths and tooling that take cutting‑edge research models into production for NVIDIA’s inference microservices and NIMs offerings.
Responsibilities
- Optimize diffusion and visual generative models for low‑latency, high‑throughput inference on NVIDIA GPUs.
- Convert, deploy, and tune models using frameworks such as TensorRT, TensorRT‑LLM, and vLLM.
- Profile and optimize deep learning workloads across the NVIDIA hardware/software stack.
- Collaborate with internal and partner research scientists and engineers to move models from prototype to production.
- Contribute to automation and tooling for NVIDIA Inference Microservices (NIMs), including performance benchmarking and regression tracking.
Benefits
Highly competitive salary, equity, and comprehensive benefits (healthcare, retirement, etc.) as described across NVIDIA job family and salary resources.Work with world‑class research scientists, software engineers, and hardware experts on state‑of‑the‑art generative AI systems.Fast‑paced, high‑impact environment with significant ownership over production AI infrastructure.
Category
LLM / Generative AI Engineer