AI Automation Engineer

The Strategy, Portfolio and Governance office runs a steady stream of recurring, high-visibility analysis and reporting for Roman Vorel's ESET org — CW/vendor cost and SOW reconciliation, org-change and headcount documentation, executive reporting (MPRs, leadership decks), hiring job descriptions, and AI-adoption reporting. We are looking for one hands-on engineer to build and maintain Claude Skills, Plugins, and lightweight MCP integrations on PayPal's internal Cosmos AI platform that turn this recurring work into governed, repeatable, self-service automation for Strategy, Portfolio and Governance — reducing manual spreadsheet/deck assembly so the office can focus on judgment calls, not data wrangling. Key Responsibilities ● Build and maintain Claude Skills/Plugins for Strategy, Portfolio and Governance's recurring deliverables: CW/vendor cost-split analysis (SOW-level $ by support tier, supplier reconciliation to source-of-truth totals), org-change one-pagers, MPR pre-read assembly, AI-adoption reporting, and hiring job description generation. ● Automate data pulls and reconciliation from source systems — Workday (org/headcount), ServiceNow SPM/Master Portfolio, CW expense/SOW spreadsheets, and SharePoint/M365 — into standardized Strategy, Portfolio and Governance reporting formats, with built-in checks against known source totals. ● Develop and register lightweight MCP server integrations connecting Claude/Claude Code to the systems the Strategy, Portfolio and Governance office relies on day to day (Workday, ServiceNow, SharePoint/M365, Slack, Jira/Confluence) via PayPal's Cosmos AI Nexus MCP Hub. ● Certify and publish skills/plugins through the Cosmos Skills & Plugin Registry, meeting taxonomy, metadata, and CI compliance-validation requirements. ● Apply RBAC and data-handling guardrails correctly given the sensitivity of what flows through these tools — unannounced org changes, headcount/hiring plans, and vendor financials — so nothing is exposed outside a strict need-to-know. ● Work directly with Pallavi to translate ad hoc and recurring Strategy, Portfolio and Governance asks into repeatable automation, iterating quickly as reporting needs shift week to week. ● Maintain clear documentation for each skill/plugin (purpose, inputs/outputs, data sources, owner) and provide day-two support/maintenance once in production. Required Skills & Experience ● 3+ years of software engineering experience, with solid proficiency in Python and/or Node.js/TypeScript. ● Hands-on experience building with Claude Code / Claude Skills or an equivalent agentic coding assistant (e.g., OpenAI Codex, Cursor), including the skill/plugin packaging model (SKILL.md-style definitions, front-matter, tool scoping). ● Working knowledge of the Model Context Protocol (MCP) — building, deploying, and registering MCP servers; comfortable with OAuth/SSO-based auth patterns. ● Experience integrating with enterprise SaaS APIs and data sources — Workday, ServiceNow, Microsoft 365/SharePoint, Atlassian (Jira/Confluence), Slack — plus strong Excel/spreadsheet automation (formulas, pivots, reconciliation logic). ● Understanding of data classification and AI governance concepts (PII handling, RBAC, guardrails) in an enterprise setting. ● High discretion with confidential material — org-change plans, headcount, and vendor financials — before they're announced or finalized. ● Strong written communication — comfortable working directly with an executive office to scope fast-turnaround, judgment-sensitive asks. Preferred / Nice to Have ● Prior exposure to financial/budget analysis, vendor cost reconciliation, or contingent-workforce (SOW) reporting. ● Familiarity with data engineering (SQL) and business intelligence tools (Looker, Power BI, Tableau) ● Prior work on an internal AI/automation platform team, or with a skills/plugin/tool registry and its certification pipeline.