Senior Software Engineer, AI Agent Runtime and Open Source Infrastructure

Responsibilities

• Build and implement production-grade features across NemoClaw, including onboarding flows, policy controls, inference routing, and sandbox lifecycle.
• Develop and sustain secure agent runtime infrastructure with a focus on network policy administration, credential management, and failure recovery.
• Engage in daily open-source workflows by authoring pull requests, conducting technical reviews, and contributing to documentation.
• Utilize AI-assisted development tools to enhance the engineering loop while maintaining rigorous verification and security standards.
• Develop automation scripts, test harnesses, and CI/CD workflows to improve team efficiency.
• Diagnose and resolve complex failures across diverse environments, including TypeScript/Node.js, containers, Linux, macOS, and GPU-backed systems.
• Collaborate with internal teams and external open-source communities.

Requirements

• BS, MS, or equivalent experience in Computer Science, Software Engineering, or a related technical field.
• 12+ years of experience in developing and managing production software systems, developer infrastructure, or open-source platforms.
• Strong systems engineering fundamentals and a proven track record of solving multifaceted technical problems.
• Proficiency in at least one major programming language with the ability to rapidly master TypeScript, JavaScript, Node.js, and Rust.
• Experience working within large codebases, including reading unfamiliar code and conducting detailed technical reviews.
• Demonstrated experience with open-source practices, such as managing pull requests and public technical discussions.
• Security-conscious engineering approach, specifically regarding sandboxing, secrets management, and network policy enforcement.
• Strong testing, debugging, and CI/CD abilities, including the capacity to replicate failures and determine root causes.

Preferred Qualifications

• Contributions to open-source developer infrastructure, AI tooling, or large-scale public software projects.
• Hands-on experience with AI coding agents, multi-agent systems, or workflow automation.
• Experience with containerization and Linux isolation technologies (e.g., Docker, Kubernetes).
• Familiarity with LLM inference, GPU-backed workloads, or performance-sensitive AI infrastructure.

About the Company

NVIDIA is a global leader in accelerated computing, transforming industries through AI, high-performance computing, and visualization. Our GPUs serve as the brains for the next era of computing, powering everything from robots to self-driving cars.