NVIDIA
Senior System Software Engineer - Dynamo-Triton Inference Server
$152K–$288K
US, CA, Santa Clara +2 · Senior · Full-time · Posted Jul 2, 2026
- Location
- US, CA, Santa Clara
US, CA, Remote
US, WA, Seattle - Experience
- 5+ years of professional experience working on deep learning software.
- Education
- MS or PhD in Computer Science or relevant field (or equivalent experience).
About the job
Develop and improve a GPU-accelerated AI inference platform, including integrating Triton Inference Server and NVIDIA Dynamo to serve LLM and non-LLM workloads.
What you'll do
- Develop inference-serving software and features, encouraging broad customer adoption.
- Help unify Triton Inference Server and NVIDIA Dynamo into a high-performance platform for LLM and non-LLM workloads.
- Build production-ready software and balance prediction throughput and latency while advancing inference technologies.
What they ask for
- MS or PhD in Computer Science or a relevant field, or equivalent experience.
- 5+ years of professional experience working on deep learning software.
- Excellent Rust and C++ skills, familiarity with Python, and strong software design, debugging, performance analysis, and test-design skills.
- Experience with high-scale distributed systems and ML systems.
Nice to have
- Experience with AI frameworks or engines such as TensorRT, PyTorch, ONNX, OpenVINO, vLLM, or TRT-LLM.
- Knowledge of GPU or cache management, high-performance networking, distributed systems programming, or contributing to a large open-source project.
Pay
152,000 USD - 241,500 USD (base salary, Level 3); 184,000 USD - 287,500 USD (base salary, Level 4)
Tools
Rust, C++, Python, Triton Inference Server, NVIDIA Dynamo, TensorRT, PyTorch, ONNX
AI focus
Develop a high-performance GPU-accelerated inference platform for LLM and non-LLM workloads.
Model-written summary · the original posting is authoritative