Senior AI-Native Systems Software Engineer, TensorRT

Details

Are you passionate about redefining how software is built in the age of Generative AI? Join NVIDIA’s TensorRT team to help lead a first-of-its-kind, AI-native initiative designed to make TensorRT the default entry point for out-of-framework inference globally. The team is building a framework from the ground up to leverage swarms of AI agents to produce high-performance, high-quality, modern C++ software at scale.

Responsibilities

• Architect an AI-native framework that scales beyond human capacity, supporting many AI agents working in parallel to generate, test, and validate production-grade software.
• Scale workflows via agentic tooling: build AI-native tools, multi-agent orchestrators, and codebase harnesses that let humans focus on highest-value work.
• Rapid prototyping with state-of-the-art models: scout industry and academic breakthroughs (e.g., attention mechanisms, KV cache strategies) and dispatch agent swarms to prototype and integrate capabilities.
• Deliver a great user experience: ensure a seamless, high-performance path to production for modern model families (LLMs, Diffusion, Audio, Vision, and multi-modal models).
• Extreme performance optimization: work at the intersection of Python orchestration and C++ engine-level optimizations to achieve major latency and throughput gains for critical customer use cases.

Requirements

• BS, MS, or PhD in Computer Science, Computer Engineering, AI, or equivalent experience.
• 4+ years of relevant software development experience.
• Strong modern C++ skills: proficiency with C++11/14/17 (or newer) and the STL; emphasis on clean, maintainable, performant code.
• Deep learning familiarity: experience with modern inference frameworks and an understanding of architectural nuances of LLMs, Diffusion, and multi-modal models.
• Systems thinking: interest in evolving software architecture to support automated, agent-driven development and indefinitely scaling codebases.
• End-to-end product sense: ability to translate high-level customer needs into concrete technical requirements and user-centric solutions.
• Pragmatic execution: demonstrated ability to deliver production-quality software on tight timelines.
• Collaborative mindset: excellent communication skills and comfort working across internal organizations and with customers.

Ways to stand out

• Hands-on experience with AI agent orchestrators or multi-agent coding frameworks, or experience building custom agentic coding harnesses for production software.
• CUDA and kernel expertise, or exposure to kernel generation / autotuning efforts.
• Track record of rapidly turning state-of-the-art papers into working prototypes in days.
• Expertise in software performance analysis, profiling, and optimization (CPU and/or GPU), including tooling-driven improvements.

Compensation & Benefits

• Base salary ranges (location and level dependent):
  • Level 3: 152,000 USD - 241,500 USD
  • Level 4: 184,000 USD - 287,500 USD
• Eligible for equity and company benefits (see NVIDIA benefits page).

Additional information

• #LI-Hybrid (hybrid work arrangement).
• Applications accepted at least until April 25, 2026.
• NVIDIA uses AI tools in its recruiting processes and is an equal opportunity employer.