Senior Staff Engineer, Enterprise Saas Platform and Automation

NVIDIA NVIDIA · Semiconductors · Santa Clara, CA

Senior Staff Engineer role focused on building agentic systems and AI-powered automation for enterprise SaaS platforms, including onboarding, support, and vendor integration. The role involves designing and implementing solutions using Python, APIs, and LLMs to reduce manual processes and improve employee productivity.

What you'd actually do

  1. Design and build agentic systems that automate the full SaaS application lifecycle — onboarding, provisioning, support triage, offboarding — eliminating manual processes across the IT SaaS portfolio.
  2. Architect and implement automation and integration solutions across Microsoft 365, Slack, Glean, and other enterprise SaaS platforms; define integration patterns and engineering standards for the team.
  3. Build AI-powered support automation — intelligent triage, self-healing workflows, proactive issue detection — that reduces human intervention and improves employee experience at scale.
  4. Engineer vendor integration frameworks that automate data flows, contract triggers, and operational touchpoints between NVIDIA systems and SaaS vendors.
  5. Develop and deploy MCP-based integrations and AI agent pipelines that surface insights, automate decisions, and enable employees to get more done with less friction.

Skills

Required

  • Python
  • APIs
  • event-driven architectures
  • workflow orchestration
  • AI/ML frameworks
  • LLMs
  • agentic systems
  • enterprise SaaS platforms (Microsoft 365, Slack, or similar)
  • integration patterns
  • data models

Nice to have

  • MCP servers
  • AI agents
  • LLM-powered workflows
  • quantify automation impact
  • SaaS vendor management
  • contract integrations
  • procurement automation
  • enterprise security
  • compliance requirements for SaaS integrations (OAuth, SCIM, SSO, data residency)

What the JD emphasized

  • track record of building production-grade automation systems, integrations, or platforms at enterprise scale
  • Hands-on experience with AI/ML frameworks, LLMs, or agentic systems; demonstrated ability to apply AI to real operational problems, not just prototype it.
  • Experience building MCP servers, AI agents, or LLM-powered workflows in production environments.

Other signals

  • AI-powered support automation
  • agentic systems
  • LLM-powered workflows