AI Software Engineer

Ford Ford · Auto · Dearborn, MI +1 · Global Data Insight & Analytics

AI Software Engineer at Ford focusing on building AI-native applications and autonomous agents for marketing analytics. The role involves architecting systems where LLMs navigate business logic, utilize data protocols, and provide real-time streaming experiences. Key responsibilities include designing agentic workflows, implementing tool-use, optimizing RAG pipelines, and establishing AI evaluation and observability.

What you'd actually do

  1. Design and Build Agentic Workflows: Design and build AI-powered applications, agents, and intelligent workflows that improve discovery, recommendation, and analysis of marketing enterprise analytics assets, customer data, and media metrics.
  2. Architect Autonomous Loops: Transition from linear "chain" workflows to self-correcting agentic loops using frameworks like LangChain, LangGraph, or LlamaIndex to automate complex marketing analytics workflows.
  3. Implement Tool-Use & MCP: Design and implement robust "tool-calling" capabilities, ensuring LLMs can reliably interact with external marketing APIs, Customer Data Platforms (CDPs), and internal media databases. Build and maintain Model Context Protocol (MCP) servers to bridge the gap between LLMs and our proprietary marketing data silos securely and in real-time.
  4. Develop High-Concurrency Backends: Develop asynchronous Python (FastAPI/Flask) or Java (Spring Boot) backend services optimized for long-running AI tasks, marketing attribution modeling, and real-time token streaming.
  5. Build Streaming Frontends: Build responsive, stateful UIs in React or Angular that handle complex AI interactions (streaming text, generative UI components, and multi-modal feedback).

Skills

Required

  • 3+ years of professional experience in Software Engineering or Data Science building scalable production systems.
  • 1+ years of hands-on experience designing, training, and deploying complex AI/ML systems in production environments.
  • Experience working with Python, Java, JavaScript, or Angular programming languages.
  • Experience in building autonomous agents using agent orchestration frameworks such as LangGraph, LangChain, LlamaIndex, or similar technologies.
  • Experience implementing tool integration patterns (MCP), agent communication protocols, and AI application observability.
  • Experience with vector search, hybrid retrieval architectures, or vector databases (Chroma, Qdrant, Pinecone, pgvector).
  • Experience working with GCP services (Vertex AI, Cloud Run, and BigQuery) or similar cloud platforms for deploying scalable AI solutions.
  • Strong problem-solving and system design skills with the ability to evaluate competing technical approaches and articulate tradeoffs.
  • Solid understanding of data engineering (SQL, Spark, data pipelines) and a strong interest or experience in quantitative marketing concepts like multi-touch attribution, cohort analysis, and predictive customer lifetime value.

Nice to have

  • Experience with semantic technologies, marketing mix modeling (MMM), attribution models, or digital media analytics.
  • Experience working with graph databases, Graph-RAG applications, or knowledge graphs.
  • Experience with context optimization (prompt compression, "lost-in-the-middle" mitigation).

What the JD emphasized

  • AI-native applications
  • autonomous agents
  • LLMs aren’t just features—they are the core engine
  • AI Orchestrator
  • autonomous loops
  • tool-calling
  • AI Evals

Other signals

  • AI-native applications
  • autonomous agents
  • LLMs as core engine
  • streaming experiences