Staff Software Engineer - Agentic Automation

NVIDIA•Santa Clara, CA

About The Position

NVIDIA is hiring an engineer to own engineering efforts across its enterprise systems. Working with IT leadership, the engineer will help transform reactive support into strategic, AI-infused automated resolution systems that prevent problems before they occur while balancing speed, security, and user experience. The role designs and implements agentic AI workflows and robust integrations and automation pipelines across enterprise platforms. It owns work spanning infrastructure through user-facing tools, helps resolve enterprise issues, improves mitigation and resolution times, and strengthens team capabilities through documentation and mentorship.

Requirements

Bachelor’s degree or equivalent experience.
At least 8 years of experience in SRE, Enterprise Support, or DevOps.
Experience with SaaS, hybrid cloud, and AI/ML environments.
Experience building production-grade agentic workflows, such as multi-agent systems and MCP servers.
Software engineering fundamentals and deep experience building products and operating large-scale systems.

Responsibilities

Design and implement agentic AI workflows using LLM-based agents, tool calling, RAG patterns, and orchestration frameworks.
Build integrations and automation pipelines across ServiceNow, identity management, monitoring platforms, and enterprise SaaS.
Own the full stack, from infrastructure to user-facing tools.
Triage and resolve enterprise issues, emphasizing automation and improved mitigation and resolution times.
Manage and troubleshoot enterprise-scale collaboration, productivity, AI, and infrastructure systems.
Trace and identify root causes of complex, multi-system failures.
Identify patterns in recurring tickets and build automation or self-service solutions.
Build and maintain runbooks, troubleshooting guides, and knowledge base articles.
Mentor team members on troubleshooting methodology and systems thinking.