AI Engineer

In this role, you will act as a force multiplier for our quantitative analytics teams. Your primary mission will be to design, build, and deploy Generative AI tools and Large Language Model (LLM) applications that assist our analytical modelers in their day-to-day work. Whether it is building AI co-pilots for code generation, creating automated model-documentation generators, you will build the AI infrastructure that makes our FC risk team faster, more efficient, and more innovative.

• Internal AI Tool Development: Architect and build LLM-powered applications, AI agents, and workflow automations specifically designed to assist model validators and quantitative modelers (e.g., Independent validation agents, code-generation agents, and Monitoring agents).
• AI-Ops & Infrastructure (LLMOps): Establish robust AI-Ops pipelines to manage the end-to-end lifecycle of Generative AI tools. Implement automated deployment, version control, prompt tracking, and continuous monitoring for model performance and hallucination mitigation.
• Cloud & CI/CD Engineering: Deploy highly available AI microservices using Google Cloud Platform (GCP). Manage CI/CD pipelines using Infrastructure as Code (e.g., Terraform, Cloud Build) to ensure seamless and secure continuous integration.
• User-Centric Collaboration: Work closely with analytical modelers to deeply understand their daily bottlenecks, data prep challenges, and coding workflows, translating those pain points into effective AI solutions.
• Security & Governance: Ensure all internal AI tools adhere to Ford's strict data privacy, security, and compliance standards, implementing guardrails for internal data usage.

Skills & Knowledge Required

• LLM & GenAI Technologies: Strong hands-on experience with LLM orchestration frameworks (e.g., LangChain, Google ADK, MCP), and utilizing commercial or open-source foundation models.
• AI-Ops / LLMOps: Proficiency in tools for monitoring, tracing, and evaluating LLM outputs.
• Vector Databases: Experience working with vector search technologies (e.g., GCP Vertex Vector Search, Sentence Transformer, ColBERT) for retrieval using encoder based models.
• Software Engineering: 4+ years of advanced hands-on experience with Python programming and building robust APIs (FastAPI, Flask) to serve AI models to end-users.
• Cloud Platform: Extensive experience in Google Cloud Platform (GCP), specifically with Cloud Build, Cloud Run, GCS, BigQuery.
• Analytics Workflow Understanding: Familiarity with the general workflows of data scientists and modelers (data wrangling, feature engineering, model validation) so you can effectively build tools that serve them.

• Education: Master’s or Bachelor’s degree in Computer Science, Software Engineering, Artificial Intelligence, Data Science, or a related technical discipline.
• AI/Engineering Experience: 4–7 years of overall software engineering or AI development experience (Python – PyTorch, Pandas), with at least 1–2 years of dedicated, hands-on experience building and deploying LLMs and GenAI applications into production.
• DevOps/MLOps: Proven track record of implementing CI/CD for machine learning/AI, containerization (Docker/Kubernetes), and cloud infrastructure management.
• Good to Have (Optional):
  • Previous exposure to the Banking, Financial Services, or Credit Analytics industries.
  • Familiarity with SAS to aid in building code-translation or modernization tools for modelers.