NVIDIA
Senior AI-Native Systems Software Engineer, TensorRT
$152K–$288K
US, CA, Santa Clara · Senior · Full-time · Posted Oct 26, 2026
- Experience
- 4+ years of relevant software development experience.
- Education
- BS, MS, or PhD in Computer Science, Computer Engineering, AI, or equivalent experience.
About the job
Build an AI-native, agent-driven framework for developing and scaling TensorRT inference software, while improving model onboarding and inference performance.
What you'll do
- Design architecture and tools that enable AI agents to generate, test, and validate production software in parallel.
- Prototype and integrate deep-learning breakthroughs and improve the production path for new model families.
- Optimize latency and throughput across Python orchestration and C++ engine-level software.
What they ask for
- BS, MS, or PhD in Computer Science, Computer Engineering, AI, or equivalent experience.
- 4+ years of relevant software development experience.
- Proficiency in modern C++ (C++11/14/17 or newer) and the STL.
- Experience with modern inference frameworks and understanding of LLM, Diffusion, and multi-modal model architectures.
Nice to have
- Hands-on experience with AI-agent orchestrators, multi-agent coding frameworks, or production agentic coding harnesses.
- CUDA programming or kernel generation/autotuning experience.
Pay
152,000 USD - 241,500 USD (base salary, Level 3); 184,000 USD - 287,500 USD (base salary, Level 4)
Tools
TensorRT, C++11/14/17, STL, Python, CUDA
AI focus
Build and use AI-agent swarms, orchestrators, and coding tools to develop, test, and validate software; prototype deep-learning breakthroughs and support inference for LLM, Diffusion, Audio, Vision, and multi-modal models.
Model-written summary · the original posting is authoritative