Senior Software Engineer

Ford Ford · Auto · United States · Enterprise Technology

Senior Software Engineer role focused on developing and deploying cloud applications that integrate Generative AI, LLMs, and agentic workflows for industrial data analytics at Ford. Responsibilities include full lifecycle development, AI-assisted software engineering, and modern DevOps practices.

What you'd actually do

  1. AI & Agentic Solution Development: Architect, build, and deploy LLM-powered applications, Retrieval-Augmented Generation (RAG) pipelines, and multi-agent systems to automate complex data analysis, anomaly detection, and decision-support workflows.
  2. AI-Assisted Software Engineering: Champion the use of generative AI tools and agentic coding assistants (e.g., GitHub Copilot, custom LLM agents) to streamline the software development lifecycle, automate testing, and accelerate CI/CD pipelines.
  3. Product & Requirements Management: Collaborate with cross-functional teams to translate business goals into technical requirements, user stories, and test suites within an Agile framework.
  4. Technical Design & Architecture: Author comprehensive technical design documents, system architecture diagrams, and API specifications to ensure scalable, secure, and maintainable solutions.
  5. Modern Operations & DevOps: Build robust CI/CD deployment pipelines, integrate automated security/quality scanning, and implement modern Identity & Access Management (IAM) and automated credential rotation.

Skills

Required

  • Software Engineering
  • modern frontend frameworks (Angular, React, or Vue)
  • backend frameworks (FastAPI, Flask, Django, or Spring Boot)
  • Python
  • Java
  • integrating LLM APIs (e.g., OpenAI, Anthropic, Vertex AI) or open-source models

Nice to have

  • Master’s degree in Computer Science, Computer Engineering, or a related quantitative field
  • LLM orchestration frameworks (e.g., LangChain, LlamaIndex)
  • multi-agent development platforms (e.g., CrewAI, AutoGen, Semantic Kernel)
  • vector databases (e.g., PGVector, Chroma, Pinecone, Milvus)
  • embedding techniques
  • Cloud platforms (GCP, Azure, or AWS)
  • modern CI/CD tools (Tekton, Terraform, Jenkins, Cloud Build)
  • Agile tools (Jira, Rally)

What the JD emphasized

  • AI & Agentic Solution Development
  • LLM-powered applications
  • Retrieval-Augmented Generation (RAG) pipelines
  • multi-agent systems
  • AI-Assisted Software Engineering
  • generative AI tools
  • agentic coding assistants
  • LLM APIs
  • LLM orchestration frameworks
  • multi-agent development platforms
  • vector databases

Other signals

  • Generative AI
  • Large Language Models (LLMs)
  • autonomous agentic workflows
  • LLM-powered applications
  • Retrieval-Augmented Generation (RAG) pipelines
  • multi-agent systems