Job Description

Ford Credit finances the purchase and lease of Ford vehicles for millions of customers. Behind that sit the platforms that make credit decisions, fund contracts, service accounts, process payments, and manage collections. They run at high volume, under regulation, and they have to be right every time.

Our Core Platform Engineering team builds the intelligence layer on top of those platforms. That means assistants grounded in verified company knowledge, tools that help engineers understand and rewrite decades-old code, and models that sharpen decisions the business makes about credit and recovery. Some of what we work on is new. Some of it has been running since before most of the team was born. Both are interesting problems.

We are looking for a senior engineer who can carry AI work from a promising demo to something that runs in production and stays reliable. In lending, an answer is only worth having if it can be traced and defended. You will build to that standard — grounded output, accuracy you can measure, human review where the stakes justify it, and a record of how a decision was reached.

This is a hands-on role. You will write code most days. You will also shape how the wider team builds with AI, set the guardrails, and bring other engineers up with you.

• Design, build, and operate production AI applications, including retrieval systems and agents grounded in trusted internal knowledge.
• Take features from prototype to production, and stay responsible for them once they are live.
• Build the evaluation layer: accuracy benchmarks, regression tests for prompts and retrieval, confidence thresholds, and monitoring for drift. Prove performance before claiming it.
• Integrate AI into the tools and workflows people already use, rather than asking them to work somewhere new.
• Apply AI to legacy modernization — analysing older codebases, producing functional specifications, and rebuilding capability on modern cloud services.
• Build and train models on portfolio and behavioural data, back-test against history, and work with the business to turn output into action.
• Write clean, tested Java and Python, and hold a high bar in code review.
• Own reliability for what you ship: monitoring, alerting, on-call, and fixing root causes.
• Set and enforce safe practice for AI-assisted work — reversible changes, human sign-off on high-risk items, and honest escalation when the tooling gets something wrong.
• Work directly with product owners, risk, and operations to agree what success looks like before build starts.
• Mentor engineers, review designs, and raise the output of the team, not just your own.

Required

• Bachelor's degree in Computer Science, Engineering, or a related field, or equivalent practical experience.
• 5+ years building and shipping production software, including at least 2 years on AI or LLM-based systems used by real people.
• Strong Python and Java, including Spring Boot.
• Hands-on experience with retrieval-augmented generation, embeddings and vector search, prompt design, tool and function calling, and agent orchestration.
• Experience building on a major cloud platform, ideally Google Cloud.
• Practical experience evaluating AI output — grounding, accuracy testing, and catching regressions before users do.
• API design, data pipeline development, and solid SQL.
• CI/CD, containers, automated testing, and infrastructure as code.
• Proven ownership of production services, including debugging live issues.
• Clear communication with both engineers and business teams. You can explain a trade-off to someone who does not write code.

Preferred

• Financial services, lending, or another regulated industry.
• Legacy modernization or reverse engineering of older systems, including mainframe technologies.
• Building and back-testing machine learning models on transactional or behavioural data.
• Multi-agent design, tool integration standards such as Model Context Protocol, and frameworks for agent orchestration.
• Experience with AI-assisted development across large codebases.
• Understanding of responsible AI in regulated settings: bias, explainability, and audit.
• Experience mentoring engineers or setting technical direction for a small team.
• Master's degree in Computer Science, Artificial Intelligence, Machine Learning, or Data Science.
• Cloud or machine learning professional certification.