Systems Engineer – End-to-end Software Diagnostics & Observability

Ford Ford · Auto · Dearborn, MI +1 · PD Operations and Quality

Ford is building an AI-powered End-to-End Software Diagnostics & Observability platform for modern vehicles. This role focuses on engineering AI-driven diagnostic capabilities, combining vehicle signals with LLM-based reasoning (RAG) to automate root-cause isolation and improve the ownership and service experience. The role involves full-lifecycle ownership from embedded systems to cloud services and AI/ML integration.

What you'd actually do

  1. Partner with cross-functional teams to define "what" a vehicle needs to observe, write the technical requirements (ECU logging/Cloud interpretation), and lead the integration through to global production monitoring.
  2. Define and enforce the "Definition of Done" for diagnostic workflows. You are essential to ensuring that code is not only functional but observable, maintainable, and meets Ford’s rigorous production benchmarks.
  3. Tailor system behavior and data visualization for a diverse user base. Ensure a 3rd-party technician gets a "repair hint," a remote driver experiences a seamless fix, and an enterprise engineer receives high-fidelity raw telemetry.
  4. Distill complex system telemetry into actionable insights. You must be able to communicate technical tradeoffs and root-cause analyses clearly to both deep-tech engineering teams and non-technical leadership.
  5. Engineer AI-powered diagnostic capabilities that combine vehicle signals (DTCs, PIDs, Ethernet logs) with LLM-based reasoning (RAG) to automate root-cause isolation.

Skills

Required

  • BS or equivalent or higher degree in Computer Science, Systems Engineering, Electrical Engineering, or a related technical field.
  • Python & Automation Mastery: 1+ years of experience writing 2,000+ lines of clean, PEP8 compliant, modular Python code for data processing, API integration, or system automation.
  • Production System Integration: 1+ years of experience with Git-based version control (minimum 50+ commits/merges) and containerization (Docker), including deploying at least 3 containerized applications to a cloud or local environment.
  • AI/ML Implementation: 1+ years of professional/research experience in at least 2 end-to-end AI/ML projects involving LLM orchestration (e.g., LangChain) or deploying a reasoning agent into a "live" state.
  • Data Integrity: 1+ years of experience processing and cleaning datasets exceeding 10,000+ records for model training or inference.
  • Technical Documentation: 1+ years of experience translating ambiguity into structure by authoring at least 3-5 detailed technical specifications (e.g., API contracts, System Requirements, or Sequence Diagrams).
  • Problem Solving: 1+ years of experience debugging complex systems (Embedded or Cloud), resolving at least 5-10 high-impact issues.

Nice to have

  • Minimum 3.5 cumulative GPA (or equivalent evidence of technical rigor).

What the JD emphasized

  • AI/ML implementation
  • LLM orchestration
  • deploying a reasoning agent into a "live" state
  • AI-powered diagnostic capabilities
  • LLM-based reasoning (RAG)

Other signals

  • AI-powered Embedded Vehicle Diagnostics
  • End-to-End Software Diagnostics & Observability platform
  • AI/ML Engineering
  • LLM-based reasoning (RAG)