Senior Software Engineer - Distributed Inference

NVIDIA has been transforming computer graphics, PC gaming, and accelerated computing for more than 25 years. It’s a unique legacy of innovation that’s fueled by great technology—and amazing people. Today, we’re tapping into the unlimited potential of AI to define the next era of computing. An era in which our GPU acts as the brains of computers, robots, and self-driving cars that can understand the world. Doing what’s never been done before takes vision, innovation, and the world’s best talent. As an NVIDIAN, you’ll be immersed in a diverse, supportive environment where everyone is inspired to do their best work. Come join the team and see how you can make a lasting impact on the world.

We are now looking for a Senior System Software Engineer to work on user facing tools for Triton Inference Server! NVIDIA is hiring software engineers for its GPU-accelerated deep learning software team, and we are a remote friendly work environment. Academic and commercial groups around the world are using GPUs to power a revolution in deep learning, enabling breakthroughs in problems from LLM, image classification to speech recognition to natural language processing. We are a fast-paced team building tools and software to make the design and deployment of new deep learning models easier and accessible to more data scientists.

What you'll be doing:

• Develop and enhance functionalities within the GenAI-Perf, Triton Performance Analyzer and Triton Model Analyzer tools.

• Collaborate with researchers and engineers to understand their performance analysis needs and translate them into actionable features.

• Collaborate closely with cross-functional teams including software engineers, system architects, and product managers to drive performance improvements throughout the development lifecycle.

• Responsible for setting up, executing, and analyzing the performance of LLM, Generative AI and deep learning models.

• Develop and implement efficient algorithms for measuring deep learning throughput and latency, benchmarking large language models, and deploying models.

• Integrate various tools to create a unified and user-friendly experience for deep learning performance analysis.

• Automate testing processes to ensure the quality and stability of the tools.

• Contribute to technical documentation and user guides. Stay up-to-date on the latest advancements in deep learning performance analysis and LLM optimization techniques.

What we need to see:

• Bachelor's, Masters or PhD or equivalent experience

• 8+ years in Computer Science, computer architecture, or related field

• Knowledge of distributed systems programming.

• Ability to work in a fast-paced, agile team environment

• Excellent Python programming and software design skills, including debugging, performance analysis, and test design.

Ways to stand out from the crowd:

• Experience with deep learning algorithms and frameworks. Especially experience with Large Language Models and frameworks such as PyTorch, TensorFlow, TensorRT, and ONNX Runtime.

• Excellent troubleshooting abilities spanning multiple software (storage systems, kernels and containers).

• Experience contributing to a large open source project - use of GitHub, bug tracking, branching and merging code, OSS licensing issues handling patches, etc.

• Familiarity with cloud computing platforms (e.g., AWS, Azure, GCP) and Experience building and deploying cloud services using HTTP REST, gRPC, protobuf, JSON and related technologies.

• Experience working with NVIDIA GPUs and deep learning inference frameworks is a plus.

NVIDIA has continuously reinvented itself over three decades. Our invention of the GPU in 1999 sparked the growth of the PC gaming market, redefined modern computer graphics, and revolutionized parallel computing. More recently, GPU deep learning ignited modern AI — the next era of computing. We are widely considered to be the leader of AI computing, and one of the technology world’s most desirable employers. We have some of the most forward-thinking and committed people in the world working for us. If you're creative and autonomous, we want to hear from you!