About the job
NVIDIA is seeking an engineering manager to lead engineering activities related to productizing Deep Learning models. Academic and commercial groups around the world are using GPUs to redefine Artificial Intelligence and data analytics, and to power data centers. Join the team building software which will be used by the entire world. Interact with the scientific community to implement and improve the latest algorithms. Ability to work in a multifaceted, product-centric environment is required and excellent interpersonal skills are also a requirement.
Responsibilities
Plan, schedule, mentor, and lead the execution of projects and activities of the team. Including creating, optimizing, and deploying inference DL workloads.
Collaborate with internal customers to align priorities across business units
Coordinate projects across different geographic locations
Grow and develop a world-class team
Travel to conferences, other sites, or visit customers occasionally
Qualifications
Minimum
Minimum requirement of BSc or equivalent experience
8+ overall years related of overall experience, including 3 years of management/leadership experience
Experience leading multiple software engineering projects
Strong experience with Large Language Models (LLMs) and Large Visual-Language Models (VLMs)
Excellent programming, debugging, performance analysis, and test design skills
Great communication
Preferred
Experience with inference of DL models
Experience doing performance analysis and tuning
Exposure to inference platforms such as TensorRT-LLM, vLLM, and SGLang
Project management tools (e.g. JIRA, Microsoft Project)