Nvidia
Senior Software Engineer - VLM Microservices for Neural Reconstruction
Found: Today
This role is based in Santa Clara, CA or Redmond, WA.
Compensation:
$152,000 - $287,500/year
Responsibilities:
- Design, build, and optimize containerized inference execution for 3D Vision Language Models.
- Develop benchmarks to validate model accuracy and performance.
- Release and maintain models and their pipelines throughout their lifecycle.
- Contribute to open-source projects related to VLM.
- Collaborate with Research and Product teams.
Requirements:
- Master's in Computer Science or Electrical Engineering + 3 years, or Bachelor's + 5 years of experience.
- Experience with AI distributed systems, backend services, and cloud technologies.
- Expertise in Docker, Kubernetes, REST, gRPC, and Helm.
- Proficiency in Python and C++.
- Strong software engineering fundamentals.
Tech stack:
Docker, Kubernetes, vLLM, SGLang, Torch, TRT, TRT-LLM.