Principal Data Engineer - AI

As Opus 2 continues to embed AI into our platform, we need robust, scalable data systems that power intelligent workflows and support advanced model behaviours. From retrieval and context enrichment to decision-making. You’ll architect and implement the pipelines and infrastructure that allow our AI features to operate reliably and efficiently in production, whether extending existing systems or building new foundations.

What you'll be doing

• Design and maintain pipelines that support LLM-based features — including metadata processing, semantic enrichment, and structured context retrieval.
• Design infrastructure for scalable and performant RAG systems (retrieval-augmented generation), including support for Graph RAG where adopted.
• Experience in processing large volumes and varieties of structured text data. Experience with legal documents would be a bonus.
• Collaborate closely with product, datascience, and platform teams to align data systems with evolving model and workflow needs.
• Ensure systems are observable, cost-efficient, and built with reusability and scalability in mind.
• Support experimentation and iteration with rapid prototyping pipelines that transition smoothly into production environments.

What excites us?

We’re here to ship real AI features, not experiments. We want engineers who can help squads own the full lifecycle: plan, build, test, deploy, and maintain AI powered functionality as part of their delivery flow. We’re looking to find the right person for this role, so we’ll be explicit about the opportunity and what it takes to be successful. We’re building now and are hoping to find our next teammate to start as soon as they are available.

What we're looking for in you

• You are curious and always looking to learn and grow in your craft.
• You thrive on building data systems that enable advanced features, not just move bytes around.
• You’ve worked with vector stores and embedding pipelines. You are excited by newer patterns like hybrid and graph-based retrieval (Graph RAG).
• You’re comfortable owning your systems in production and instrumenting them for observability.
• You value collaboration and can flex across infrastructure, science, and product conversations.

Qualifications

• 5+ years of experience working in a software engineering role.
• 3+ years of experience building and maintaining production-grade data infrastructure, preferably for ML/AI use cases with 1+ years working with LLM’s.
• Proficiency with AWS data tooling and cloud-native services; experience with Amazon Bedrock or Claude integration is a plus.
• Experience with vector databases and embedding pipelines.
• Familiarity with or interest in graph-based data models and Graph RAG architectures is a strong plus.
• Working knowledge of Java and TypeScript environments, especially for integration and debugging.
• Experience using Jira to coordinate delivery.

Working for Opus 2

Opus 2 is a global leader in legal software and services, trusted partner of the world’s leading legal teams. All our achievements are underpinned by our unique culture where our people are our most valuable asset. Working at Opus 2, you’ll receive:

• Contributory pension plan.
• 26 days annual holidays, hybrid working, and length of service entitlement.
• Health Insurance.
• Loyalty Share Scheme.
• Enhanced Maternity and Paternity.
• Employee Assistance Programme.
• Electric Vehicle Salary Sacrifice.
• Cycle to Work Scheme.
• Calm and Mindfulness sessions.
• A day of leave to volunteer for charity or dependent cover.
• Accessible and modern office space and regular company social events.

#J-18808-Ljbffr