Senior AI-Native Systems Software Engineer, TensorRT

NVIDIA•Santa Clara, CA

10d•$152,000 - $287,500

About The Position

Join NVIDIA’s TensorRT team to lead a first-of-its-kind, AI-native initiative intended to make TensorRT the default entry point for out-of-framework inference globally. The team is developing a framework from the ground up that uses swarms of AI agents to produce high-performance, high-quality modern C++ software at scale. The role involves designing an architecture that supports many AI agents working in parallel to generate, test, and validate production-grade software; building AI-native tools, multi-agent orchestrators, and codebase harnesses; identifying deep-learning breakthroughs and using agent swarms to prototype and integrate them; and improving the production path for current model families. The engineer will also optimize performance across Python orchestration and C++ engine-level code to improve latency and throughput for customer use cases.

Requirements

BS, MS, or PhD in Computer Science, Computer Engineering, AI, or equivalent experience.
At least 4 years of relevant software development experience.
Proficiency in modern C++ (C++11/14/17 or newer) and the STL, with an emphasis on clean, maintainable, performant code.
Experience with modern inference frameworks and understanding of architectural nuances of LLMs, Diffusion, and multimodal models.
Interest in how software architecture must evolve to support automated, agent-driven development and indefinitely scaling codebases.
Ability to translate high-level customer needs into concrete technical requirements and user-centric solutions.
Demonstrated ability to take customer requests through to production-quality software on tight timelines.
Excellent communication skills and comfort working across internal organizations and with customers.

Nice To Haves

Hands-on experience with AI agent orchestrators or multi-agent coding frameworks, or experience building custom agentic coding harnesses for production software.
Experience with CUDA programming or exposure to kernel generation or autotuning efforts.
A track record of rapidly turning state-of-the-art papers into working prototypes in days rather than weeks.
Expertise in software performance analysis, profiling, and optimization on CPU and/or GPU, using tooling to drive measurable improvements.

Responsibilities

Help design and build an AI-native codebase and architecture that scales to support large numbers of AI agents working in parallel to generate, test, and validate production-grade software.
Improve compute-to-software output by adopting and building AI-native tools, multi-agent orchestrators, and codebase harnesses.
Identify industry and academic breakthroughs, such as new attention mechanisms and KV cache strategies, and dispatch AI agent swarms to prototype and integrate them.
Deliver a seamless, high-performance path to production for LLM, Diffusion, Audio, Vision, and multimodal model families.
Optimize performance across Python orchestration and C++ engine-level code to achieve latency and throughput gains for critical customer use cases.
Translate customer needs into technical requirements and user-centric solutions, and deliver production-quality software on tight timelines.