Nvidia Senior Software Engineer Metropolis AI NIM 

United States, California 

882226994

What you’ll be doing:

• Collaborate closely with our partners and the open-source community to deliver their flagship models as highly optimized NVIDIA Inference Microservices (NIM).

• Research and develop innovative deep learning methodologies to accurately evaluate new model families across diverse domains.

• Analyze, influence, and enhance AI/DL libraries, frameworks, and APIs, ensuring consistency with the best engineering practices.

• You will design and develop accelerated streaming AI pipelines using CV and VLM models and lead technical design discussions

• Profile and optimize the AI pipelines to ensure scalability, reliability, and efficiency.

• Take on complex system-level optimization and resource utilization challenges.

• Participate in a product development lifecycle that values high standards for clear requirements, software quality and performance.

• Write code in Python and C++

What we need to see:

• BS, MS, or PhD in Computer Science, AI, Applied Math, or a related field, or equivalent experience, with 5+ years of industry experience.

• 3+ years of hands-on experience in AI for computer vision (CV) and large language models (LLMs).

• Complex system design and development using Python, C++ 14/17/20, and object-oriented programming.

• Strong problem-solving, debugging, performance analysis, test design, and documentation skills.

• Solid mathematical foundations and expertise in AI/DL algorithms.

• Excellent written and verbal communication skills, with the ability to work both independently and collaboratively in a fast-paced environment.

• Passion for expanding your technical knowledge into new areas.

• Ability to excel in a multinational, multi-time-zone environment: excellent communication skill (verbal & written), collaborates well, represents our core values.

Ways to stand out from the crowd:

• Demonstrated implementation of computer vision / machine learning applications, microservices, container and cloud-native application development.

• Experience with cloud native architecture involving dockers, k8s, microservices.

• Hands-on experience with inference and deployment environments like TensorRT, ONNX, Triton, or vLLM.

• Experience working with High Availability environments