Nvidia Manager Deep Learning Inference - ONNX 

United States, California 

656204617

What you'll be doing:

In this role, you will help shape the strategy for inference deployment workflows and lead the ONNX development efforts at NVIDIA.

• Help define and drive ONNX inference workflows and development objectives

• Collaborate closely with industry partners in advancing ONNX

• Coordinate planning and execution of inference strategy in concert with various internal teams at NVIDIA

• Grow and develop a team of world-class engineers

What we need to see:

• Masters (or equivalent experience) or PhD and at last 12 overall years of relevant industry experience in Computer Science, Artificial Intelligence, Applied Math, or related field

• 5+ years of demonstrated experience in leading and mentoring multiple software engineering teams

• Strong experience with C++11/C++14

• Working knowledge or experience with TensorRT, PyTorch, TensorFlow, JAX, ONNX Runtime or other ML frameworks.

• Excellent understanding of software development practices including architecting, development, testing, continuous integration, and documentation

• Excellent communication skills, strong analytical, and organization skills

Ways to Stand Out From the Crowd:

• Significant contributions to Deep Learning optimizations for inference.

• Strong Python programming experience

• Familiarity with CUDA kernel programming

• Experience working directly with AI hardware and software development teams.

• Exceptional project management skills, with a demonstrated ability to lead complex projects to completion.

• A charismatic leader who inspires innovation and drives the team towards achieving NVIDIA's vision.

NVIDIA has been transforming computer graphics, PC gaming, and accelerated computing for more than 25 years. It’s an outstanding legacy of innovation that’s fueled by phenomenal technology—and amazing people.