AI Inference Research Engineer

NVIDIA is seeking an AI Inference Research Engineer to join our team. You will be working on developing a world-class understanding of coding agent workloads and partnering with teams across NVIDIA's hardware and software stack to push the coding agent ecosystem to the frontier of performance.

Responsibilities:

• Building and modifying coding agent harnesses to research the impact of different architectural decisions
• Architecting AI-driven systems that analyze inference workload dynamics of leading agentic harnesses under realistic conditions
• Collaborating with teams across NVIDIA's software and hardware stack to extend co-design to the harness layer

Requirements:

• Proven track record building or modifying coding agent harnesses at scale
• Familiarity with agent evaluation frameworks such as Harbor, and inference performance metrics including TTFT, throughput, and ITL
• Hands-on use of frontier coding agents such as Codex and Claude Code, driving performance to the frontier
• Rigorous, scientific approach to data collection, analysis, and research
• BS in Computer Science or a related field, or equivalent experience

Nice to Have:

• Work experience at an AI inference or agent company
• Experience with building modern agentic or AI-backed systems
• Ability to translate data into specific product improvements with the end user in mind
• Open source projects showcasing agentic AI applications
• MS in Computer Science or a related field

Your base salary will be determined based on your location, experience, and the pay of employees in similar positions. The base salary range is 108,000 USD - 178,250 USD for Level 1, and 124,000 USD - 195,500 USD for Level 2. You will also be eligible for equity and benefits.