Software Engineer

Ford Motor Credit Company's Pinnacle Loan Originations platform underwrites and funds a significant share of the vehicles Ford sells worldwide. It is a mission-critical, multi-tier system: a mainframe core (COBOL, DB2, CICS) that executes the money-path decisioning, a Java/Spring services tier that orchestrates business workflows, GCP Cloud Run microservices at the digital edge, and Splunk-driven observability across the estate.

We are building an AI enablement layer on top of this platform — a set of production capabilities that make Pinnacle faster to operate, easier to debug, and more discoverable to the engineers and analysts who depend on it.

What you'll do: Diagnose production issues across the mainframe (COBOL, DB2, CICS), the Java/Spring services tier, and Cloud Run microservices. Ship the fix on the money-path and the corresponding improvement to agent tooling and knowledge substrate in the same change set. Design and operate the MCP tools layer. Build least-privilege, per-call-audited MCP servers over DB2, Splunk, and GCP. Build production multi-agent workflows on Google ADK for Splunk to DB2 to GCP error triage, ADR authoring, and originations debugging.

Bachelor's or Master's degree in Computer Science, Information Systems, or a related field — or equivalent professional experience. 7+ years building and operating production-grade backend systems as a hands-on engineer. 5+ years in Python and Java (Kotlin, TypeScript a plus). At least 1 year of experience in shipping AI-enabled applications in production — agent frameworks, retrieval systems, or LLM-backed services. Comfort operating in complex, multi-tier, legacy-integrated environments where change control and auditability matter. Preferred: Experience integrating with mainframe systems (COBOL, DB2 for z/OS, CICS) or comparable long-lived transactional cores.