Senior System Software Engineer – Accelerated Microservices and Libraries
NVIDIA
NVIDIA
Join our innovative engineering team as a Senior System Software Engineer, focusing on the development of high-performance microservices and libraries for our cutting-edge harnesses and agents. You'll be instrumental in designing, building, and optimizing these critical components, contributing to advancements in real-time AI applications.
This role offers an exciting opportunity to shape the future of accelerated microservices and libraries. You will collaborate closely with product management and fellow engineers to transform visionary requirements into tangible, impactful deliverables. We are seeking individuals passionate about solving complex, real-world problems with AI.
Develop and refine accelerated microservices and libraries, ensuring optimal performance and scalability.
Collaborate with engineering and product management to define project scope and translate requirements into actionable development plans.
Design, build, and maintain sophisticated microservices for real-time vision-language model inference, covering the entire pipeline from data ingestion to integration.
Create and manage automated regression tests for functional accuracy and performance, ensuring component readiness through release and beyond.
Profile and enhance end-to-end latency, throughput, GPU memory utilization, and concurrent user capacity across diverse platforms.
Possess a Master's or Bachelor's degree in Computer Science or a related engineering discipline.
Bring over 8 years of comprehensive software development experience, with a robust understanding of software design principles.
Demonstrate strong programming proficiency in C/C++ and Python.
Exhibit hands-on experience in building microservices leveraging containerization, REST APIs, and asynchronous messaging patterns.
Showcase practical experience integrating and deploying computer vision and vision-language models in production environments.
Understand real-time video processing nuances, including the trade-offs between latency, throughput, and resource management, coupled with exceptional debugging skills.
Nvidia
AI / Machine Learning