Senior Software Engineer-Distributed Inference

NVIDIA is the world leader in accelerated computing, pioneering GPU technology and AI solutions.
$184,000 - $356,500
Distributed Systems
Senior Software Engineer
Remote
5,000+ Employees
8+ years of experience
AI

Description For Senior Software Engineer-Distributed Inference

NVIDIA is seeking a Senior Software Engineer to join their GPU-accelerated deep learning software team, focusing on the Triton Inference Server. This role combines distributed systems expertise with cutting-edge AI technology, working on performance analysis and optimization of large language models and deep learning systems. The position offers the opportunity to work with NVIDIA's industry-leading GPU technology and contribute to tools that make deep learning more accessible to data scientists worldwide.

The role involves developing and enhancing performance analysis tools, collaborating with researchers and engineers, and implementing efficient algorithms for measuring deep learning throughput and latency. You'll be working in a remote-friendly environment, contributing to NVIDIA's mission of transforming computing through AI innovation.

The ideal candidate will bring 8+ years of experience in computer science or related fields, strong Python programming skills, and knowledge of distributed systems. Experience with deep learning frameworks, cloud platforms, and NVIDIA GPUs is highly valued. This position offers competitive compensation, including a base salary range of $184,000 - $356,500, plus equity and benefits.

NVIDIA's legacy of innovation spans over 25 years in computer graphics, PC gaming, and accelerated computing. The company is at the forefront of AI computing, defining the next era where GPUs power computers, robots, and self-driving cars. This role presents an exciting opportunity to make a lasting impact in the field of AI and deep learning while working with some of the industry's best talent in a diverse and supportive environment.

Last updated 5 hours ago

Responsibilities For Senior Software Engineer-Distributed Inference

  • 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
  • Drive performance improvements throughout the development lifecycle
  • Set up, execute, and analyze the performance of LLM, Generative AI and deep learning models
  • Develop algorithms for measuring deep learning throughput and latency
  • Integrate various tools for deep learning performance analysis
  • Automate testing processes
  • Contribute to technical documentation and user guides

Requirements For Senior Software Engineer-Distributed Inference

Python
  • Bachelor's, Masters or PhD or equivalent experience
  • 8+ years in Computer Science, computer architecture, or related field
  • Knowledge of distributed systems programming
  • Excellent Python programming and software design skills
  • Experience with deep learning algorithms and frameworks
  • Experience with PyTorch, TensorFlow, TensorRT, and ONNX Runtime
  • Experience with cloud computing platforms (AWS, Azure, GCP)
  • Experience with HTTP REST, gRPC, protobuf, JSON

Benefits For Senior Software Engineer-Distributed Inference

Equity
  • Equity

Interested in this job?

Jobs Related To NVIDIA Senior Software Engineer-Distributed Inference

Senior HPC Performance Engineer

Senior HPC Performance Engineer role at NVIDIA focusing on GPU Communications Libraries and Networking, optimizing performance for deep learning and HPC applications.

Senior Generalist Software Engineer -- Omniverse

Senior Generalist Software Engineer position at NVIDIA focusing on Omniverse, computer graphics, and compute systems development in Taiwan.

Senior AI-HPC Storage Engineer

Senior AI-HPC Storage Engineer role at NVIDIA, focusing on designing and implementing distributed storage solutions for AI and HPC workloads, offering competitive compensation and benefits.

Senior System Software Engineer, NCCL - Partner Enablement

Senior System Software Engineer position at NVIDIA focusing on NCCL partner enablement, combining distributed systems expertise with customer support for AI and HPC applications.

Senior GPU Cluster Software Engineer

Senior GPU Cluster Software Engineer position at NVIDIA, focusing on building profiling solutions for large-scale ML/DL applications on GPU compute clusters.