Senior High Performance AI Engineer, Agentic AI

What you'll do

• Design and build agentic AI systems including multi-agent workflows, tool use, and memory.
• Optimize agentic systems across NVIDIA's software and hardware stack from models to GPUs.
• Build data, environments, reward systems, and evaluation frameworks to improve model capabilities.
• Develop scalable agent runtimes and orchestration systems for the CUDA ecosystem.
• Co-design systems with NVIDIA's libraries, compilers, kernels, and hardware components.
• Implement high-performance AI inference using tools like TRT-LLM, SGLang, or vLLM.
• Develop intelligent systems that reason about and operate across accelerated computing stacks.

What we're looking for

• Bachelor's degree in Computer Science, Electrical Engineering, or a related field, or equivalent experience.
• MS or PhD preferred.
• 4+ years of relevant industry or academic experience in AI systems, machine learning, compilers, high-performance computing, or related areas.
• Hands-on experience in agent systems, coding agents, reinforcement learning, or modern AI inference systems.
• Strong C/C++, Rust, and Python programming skills with solid software engineering fundamentals.
• Experience with GPU programming and performance optimization using CUDA or comparable accelerator platforms.
• Track record of building high-impact coding agents, autonomous software-engineering systems, or developer tools (preferred).
• Hands-on experience optimizing and deploying with TRT-LLM, SGLang, vLLM, or Transformer Engine (preferred).