Generative AI Engineer - Ford Pro Intelligence

Ford Pro Intelligence builds data and AI-powered products that help commercial customers manage fleets more efficiently, safely, and reliably.

Our team works across connected vehicle data, fleet operations, driver insights, service planning, charging workflows, and business intelligence to create software that helps customers make better decisions and take action.

You will design and develop LLM-powered applications that connect natural language experiences with enterprise data, cloud services, and operational workflows. You will work across agent orchestration, tool calling, prompt engineering, structured data grounding, evaluation, safety, observability, and production deployment.

This is a hands-on engineering role for someone who wants to build practical GenAI systems that solve real customer problems, not isolated prototypes.

In this role, you will:

• Ship production GenAI features that improve customer workflows
• Build reliable patterns for LLM integration, tool use, evaluation, and observability
• Improve the accuracy, latency, cost, and trustworthiness of AI-enabled systems
• Help teams move from prototypes to maintainable production services
• Partner across engineering, product, data, security, and business teams
• Contribute to responsible AI practices in an enterprise software environment

We are looking for a Generative AI Engineer to help build production AI systems for Ford Pro's commercial fleet products. This role sits at the intersection of generative AI, connected vehicle data, enterprise software, and commercial fleet operations. You will work on AI systems that support real business decisions for commercial customers. The work requires both experimentation and engineering discipline: exploring new AI capabilities while building secure, reliable, observable, and maintainable production systems. You will have the opportunity to help define how GenAI is applied in commercial mobility at enterprise scale.

Design and improve LLM-based systems that can interpret user intent, retrieve context, call tools, interact with APIs, and coordinate multi-step workflows.

Areas of work may include:

• Agent orchestration
• Tool calling and function calling
• Context and conversation state management
• Structured model outputs
• Workflow automation
• Human-in-the-loop review patterns
• Integration with backend services and enterprise APIs

Develop systems that transform complex operational signals into concise summaries, recommendations, alerts, and decision-support experiences.

The goal is to help customers move from data to action faster.

Build the foundations needed to operate GenAI systems responsibly in production, including:

• Evaluation datasets and test harnesses
• Prompt and workflow regression testing
• Groundedness and accuracy checks
• Guardrails and safety controls
• Prompt injection and misuse defenses
• Latency, cost, and quality monitoring
• Traceability for debugging AI behavior

Our environment is primarily built around Google Cloud Platform, with production services developed mainly in Python and Kotlin. You do not need experience with every tool listed below, but strong candidates should be comfortable learning across this environment.

Design and improve LLM-based systems that can interpret user intent, retrieve context, call tools, interact with APIs, and coordinate multi-step workflows.

Areas of work may include:

• Agent orchestration
• Tool calling and function calling
• Context and conversation state management
• Structured model outputs
• Workflow automation
• Human-in-the-loop review patterns
• Integration with backend services and enterprise APIs

Develop systems that transform complex operational signals into concise summaries, recommendations, alerts, and decision-support experiences.

The goal is to help customers move from data to action faster.

Build the foundations needed to operate GenAI systems responsibly in production, including:

• Evaluation datasets and test harnesses
• Prompt and workflow regression testing
• Groundedness and accuracy checks
• Guardrails and safety controls
• Prompt injection and misuse defenses
• Latency, cost, and quality monitoring
• Traceability for debugging AI behavior

Our environment is primarily built around Google Cloud Platform, with production services developed mainly in Python and Kotlin. You do not need experience with every tool listed below, but strong candidates should be comfortable learning across this environment.