> Markdown version of [/jobs/ext/2019774-principal-enterprise-data-engineer](https://www.wearedevelopers.com/jobs/ext/2019774-principal-enterprise-data-engineer). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# Principal Enterprise Data Engineer

- **Company:** FICO
- **Location:** UK (Remote available)
- **Contract:** Permanent contract
- **Skills:** Artificial Intelligence, Static Program Analysis, Encodings, Continuous Integration, Enterprise Data Management, Large Language Models, Multi-Agent Systems, Containerization, Information Technology, Codebase
- **Published:** August 11, 2026
- **Apply:** https://eu.experteer.com/career/view-jobs/principal-enterprise-data-engineer-united-kingdom-58892340

## About the Role

_ rules * Establish LLM testing infrastructure and evaluation approaches with contract testing (e.g. Pact) * Manage steering loop to prevent repeated mistakes and maintain system records of docs and context * Decide placement of controls across pre-commit, post-integration, and drift-monitoring stages * Improve observability and track metrics (PR velocity, defect escape, etc.) to guide investments * Partner with product/platform teams to translate specs into enforceable controls * Mentor engineers on harness practices and responsible use of AI tools Tasks * Bachelor's/Master's in Computer Science or related disciplines, or equivalent commercial experience * Seasoned software engineer with large, complex codebase experience and strong design/architecture focus * Hands-on experience with AI coding agents (e.g. Claude Code, Codex) and understanding of their limitations * Proven ability to build tooling across a modern stack (linters, static analysis, CI/CD, containerized environments, aaaaaa
end-to-end * Familiarity with agent instruction conventions (e.g. AGENTS.md) * Experience with spec-driven development, context engineering, agent orchestration, fitness functions, and developer-platform work * Systems mindset with ability to encode good practices into repeatable rules * Judgement on when to use deterministic controls vs. LLM-based approaches and trade-offs * Experience owning quality-gating processes and release criteria * Knowledge of security considerations for autonomous agents (prompt injection, least-privilege guardrails) * Experience with consumer/contract testing (e.g., Pact) to validate distributed service integrations * Excellent communication skills to articulate designs and drive standards Key requirements * Highly competitive compensation * benefits and rewards programs * work from home / remote (UK) * employee resource groups * social events * work/life balance

## Description

Experteer Overview In this role you will architect and own the harness environment that guides AI-generated code to production-grade quality. You will collaborate with cross-functional teams to set standards, build verification and trust mechanisms, and evolve the end-to-end lifecycle of turning model capability into reliable software. You'll shape the controls that keep AI outputs safe and maintainable, while advancing observability and release criteria. This is a hands-on, systems-focused opportunity at a leading analytics software company with global impact. Pay / Benefits * Design, build, deploy, and support harness core components (guides, feedback loops, guardrails) for production-grade engineering * Own and evolve feedforward guides and drive team-wide standardisation for correct agent behavior * Create feedback sensors (linters, static analysis, architecture-fitness tests) and verification loops * Define quality gating and release criteria for agent-produced work and escalation rules * Establish LLM testing infrastructure and evaluation approaches with contract testing (e.g. Pact) * Manage steering loop to prevent repeated mistakes and maintain system records of docs and context * Decide placement of controls across pre-commit, post-integration, and drift-monitoring stages * Improve observability and track metrics (PR velocity, defect escape, etc.) to guide investments * Partner with product/platform teams to translate specs into enforceable controls * Mentor engineers on harness practices and responsible use of AI tools Tasks * Bachelor's/Master's in Computer Science or related disciplines, or equivalent commercial experience * Seasoned software engineer with large, complex codebase experience and strong design/architecture focus * Hands-on experience with AI coding agents (e.g. Claude Code, Codex) and understanding of their limitations * Proven ability to build tooling across a modern stack (linters, static analysis, CI/CD, containerized environments, instrumentation) * Familiarity with agent instruction conventions (e.g. AGENTS.md) * Experience with spec-driven development, context engineering, agent orchestration, fitness functions, and developer-platform work * Systems mindset with ability to encode good practices into repeatable rules * Judgement on when to use deterministic controls vs. LLM-based approaches and trade-offs * Experience owning quality-gating processes and release criteria * Knowledge of security considerations for autonomous agents (prompt injection, least-privilege guardrails) * Experience with consumer/contract testing (e.g., Pact) to validate distributed service integrations * Excellent communication skills to articulate designs and drive standards Key requirements * Highly competitive compensation * benefits and rewards programs * work from home / remote (UK) * employee resource groups * social events * work/life balance


## Related Videos

- [Agentic employees in world's most downloaded FinTech app](https://www.wearedevelopers.com/videos/100123-agentic-employees-in-world-s-most-downloaded-fintech-app)
- [Getting to Know Your Legacy (System) with AI-Driven Software Archeology](https://www.wearedevelopers.com/videos/1437-getting-to-know-your-legacy-system-with-ai-driven-software-archeology)
- [A Brief History of Data Storage](https://www.wearedevelopers.com/videos/974-a-brief-history-of-data-storage)
- [Containers and Kubernetes made easy: Deep dive into Podman Desktop and new AI capabilities](https://www.wearedevelopers.com/videos/1133-containers-and-kubernetes-made-easy-deep-dive-into-podman-desktop-and-new-ai-capabilities)
- [Building a Multi-Agent Orchestration Engine That Actually Follows the Rules](https://www.wearedevelopers.com/videos/100159-building-a-multi-agent-orchestration-engine-that-actually-follows-the-rules)
- [Why your codebase lies to AI?](https://www.wearedevelopers.com/videos/100281-why-your-codebase-lies-to-ai)

## Related Articles

- [Dev Digest 132 - Binging WADFlix?](https://www.wearedevelopers.com/magazine/473-dev-digest-132-binging-wadflix)
- [Dev Digest 121 - AI goes offline](https://www.wearedevelopers.com/magazine/456-dev-digest-121-ai-goes-offline)
- [Dev Digest 120 - Apple and peers](https://www.wearedevelopers.com/magazine/455-dev-digest-120-apple-and-peers)
- [Dev Digest 150 - The shift to AI generated code, fingerprinting and OKRs vs. doing your job](https://www.wearedevelopers.com/magazine/533-dev-digest-150-the-shift-to-ai-generated-code-fingerprinting-and-okrs-vs-doing-your-job)
- [Never delegate the understanding](https://www.wearedevelopers.com/magazine/749-never-delegate-the-understanding)
- [What is Agentic Programming and Why Should Developers Care?](https://www.wearedevelopers.com/magazine/625-what-is-agentic-programming-and-why-should-developers-care)