Senior Staff Software Engineer - Agentic IT Operations

Responsibilities

• As a Senior Staff Software Engineer, you will define how NVIDIA builds and operates autonomous enterprise systems. Your influence will be measured in systems adopted, engineers elevated, and problems that stopped being problems.
• Own the technical strategy and reference architecture for agentic AI across enterprise IT : agent runtimes, tool interfaces, memory and context management, orchestration, evaluation harnesses, and safety guardrails and establish them as the standard that partner engineering organizations build on.
• Architect and personally build production agentic systems using LLM-based agents, tool calling, RAG, and orchestration frameworks, delivering AI-assisted operations across employee support, endpoint services, and IT support operations.
• Design autonomous agents that execute complex, multi-step enterprise workflows end-to-end, coordinating approvals, vendor handoffs, cross-system data reconciliation, and exception handling with human-in-the-loop controls and own the reliability, observability, failure semantics, and blast-radius controls that make…
• Own the architecture of the integration and automation platform spanning ServiceNow, ERP and procurement systems, and endpoint-management platforms, including infrastructure, data pipelines, APIs, and user-facing applications and make the build/buy/deprecate calls that shape it for the next several years.
• Define the engineering standards for how agentic systems are built, tested, evaluated, and operated: prompt and tool versioning, offline and online evals, regression suites, cost and latency budgets, security and data-governance patterns, and systematic failure-mode analysis.
• Drive technical alignment across organizational boundaries, partner engineering teams, platform owners, security, and senior leadership resolving contested architectural decisions and building consensus without formal authority.
• Multiply the organization. Mentor and grow senior and staff engineers through design partnership, code review, and technical coaching, and raise the engineering bar through the work you ship and the standards you enforce.
• What We Need To See
• Bachelor’s or Master’s degree in a related field, or equivalent experience. 12+ years of hands-on software engineering experience building and operating production systems at scale, with deep expertise in at least one of: Infrastructure, SRE, DevOps, Platform, or Production Engineering.

Languages