Senior Staff Software Engineer - Agentic IT Operations

NVIDIA•Santa Clara, CA

10d

About The Position

NVIDIA is seeking a Senior Staff Software Engineer to define the technical strategy and architecture for autonomous, AI-driven enterprise operations. This senior individual-contributor role transforms IT from manual, reactive workflows into agentic platforms operating at global scale. The engineer will own difficult technical problems, establish standards adopted by other engineering organizations, and make architectural decisions with long-term impact. The role spans agent runtimes, tool interfaces, memory and context management, orchestration, evaluation, and safety. It includes designing and personally building production agentic systems and integration platforms, while ensuring autonomy is reliable, observable, secure, and governed. The engineer will also drive technical alignment across teams and mentor senior and staff engineers.

Requirements

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.
Deep expertise in at least one of infrastructure, SRE, DevOps, platform engineering, or production engineering.
Demonstrated Senior Staff-level impact, including architectural decisions affecting multiple organizations and a record of resolving the hardest technical problems.
Deep expertise designing and shipping production software integrations, automation platforms, APIs, and data pipelines for complex enterprise operations, with ownership from design through long-term operation.
Proven experience taking agentic AI or LLM-based systems to production, including multi-step autonomous execution, tool calling, RAG, human-in-the-loop safeguards, exception handling, evaluation, governance, and measurable business outcomes.
Track record modernizing enterprise IT operations platforms, such as asset management, endpoint services, IT supply chain, or infrastructure operations, including migrating or replacing legacy systems.
Production-grade proficiency with infrastructure-as-code, CI/CD, containerization such as Kubernetes, and a cloud platform such as AWS, GCP, or Azure.
Experience with monitoring and observability tools such as Prometheus, Grafana, Datadog, PagerDuty, or similar.
Fluency in Python, Go, or equivalent languages, with the ability to architect, write, and review production-quality code.
Demonstrated ability to grow other senior engineers and establish durable engineering practices.
Ability to drive technical direction across engineering, product, and senior leadership without formal authority, and explain complex trade-offs to VP- and C-level audiences in business terms.
Exceptional interpersonal, written, and verbal communication skills.

Nice To Haves

Experience defining an agentic AI or automation platform strategy for a large enterprise and driving adoption across multiple engineering organizations.
Experience building agent orchestration frameworks, evaluation infrastructure, or LLM observability tooling as internal platforms used by other teams.
Background designing event-driven or workflow-orchestration architectures, such as Temporal, Airflow, or Kafka-based systems, for long-running, stateful enterprise processes at scale.
Deep working knowledge of ServiceNow or comparable ITSM/ERP platforms at the API and data-model level, including extending them beyond standard vendor-provided approaches.
Open-source contributions, patents, published work, or conference talks in distributed systems, automation, or applied AI.

Responsibilities

Own the technical strategy and reference architecture for enterprise agentic AI, including agent runtimes, tool interfaces, memory and context management, orchestration, evaluation harnesses, and safety guardrails.
Architect and build production agentic systems using LLM-based agents, tool calling, RAG, and orchestration frameworks for employee support, endpoint services, and IT support operations.
Design agents that execute complex, multi-step enterprise workflows, coordinating approvals, vendor handoffs, cross-system data reconciliation, and exception handling with human-in-the-loop controls.
Own reliability, observability, failure semantics, and blast-radius controls for safe enterprise-scale autonomy.
Own the architecture of an integration and automation platform spanning ServiceNow, ERP and procurement systems, and endpoint-management platforms, including infrastructure, data pipelines, APIs, and user-facing applications.
Make build, buy, and deprecate decisions that shape the platform over the next several years.
Define engineering standards for building, testing, evaluating, and operating agentic systems, including prompt and tool versioning, offline and online evaluations, regression suites, cost and latency budgets, security and data-governance patterns, and failure-mode analysis.
Drive technical alignment across partner engineering teams, platform owners, security, and senior leadership; resolve architectural disagreements and build consensus without formal authority.
Mentor and grow senior and staff engineers through design partnership, code review, and technical coaching.
Raise engineering standards through shipped work and established practices.