Senior AI Engineer

Legal AI is only as good as the knowledge behind it. At Lefebvre Sdu, we’ve been building that knowledge for 200 years. Day in, day out. Law by law. Word by word. Other legal AI tools run on our data and software. As the Dutch heart of Lefebvre Group, the European leader in legal and tax knowledge, we’re also developing our own platform:
GenIA-L, where lawyers and tax professionals don’t just get an answer, but an answer they’re willing to put their name to. More than 75,000 professionals use it every day, accounting for over €100 million ARR across Europe. We’re looking for a Senior AI Engineer to help shape how the intelligent core of that platform evolves.

GenIA-L is a research platform for legal professionals. A user asks a question. The platform searches our trusted sources and turns them into a usable answer. This is done with agents: specialised AI components that each take on part of the question and work together. In the legal domain, an answer can’t just sound convincing. It has to be correct, and you need to be able to see which source it comes from.

This isn’t a pilot: the platform is in production and used heavily every day.

As a senior, you build alongside the team, but you also keep the bigger picture in view. You know the different parts of the platform and how they affect one another. You help prioritise, spot obstacles early and make sure we’re heading in the right direction, both in how we work and technically. You look ahead: where could we go, and what do we need to know to get there?

And you help medior colleagues grow by seeing exactly where they’re stuck, without taking the work off their hands.

• You give direction to the agent architecture of GenIA-L: which specialised agents are needed and how they work together.
• You break down legal processes and translate them into technical solutions. You decide how the components are best connected.
• You make sure our knowledge packages and the pipelines behind them can scale and stay up to date. A knowledge package is an expert-reviewed set of commentary, case law, legislative history and practical guidance for each article of law.
• You build the way we measure quality. Using evaluation sets, observability and metrics, you show that answers, source attribution and reliability are genuinely improving. Not based on gut feeling, but on evidence.
• You help prioritise the team’s work and flag technical or process risks early.
• You explore new developments, test ideas in practice and turn them into proposals that make the product sharper or faster.
• You coach medior engineers and work directly with editors and subject-matter experts.

You have a realistic view of LLMs. You see what they can do, but you also know their weak spots. You follow new AI developments closely, but you don’t just follow the herd: you stay critical and aren’t afraid to say so. You can break a complex problem down into smaller pieces and keep oversight of a system with many moving parts.

You take ownership, show initiative when things aren’t yet clear and think from the customer’s problem. You enjoy helping others move forward without taking over. And you like working with lawyers and editors, because they know what a good answer looks like.

• Extensive experience in software or ML engineering, around 5 years or more. Depth in recent projects counts for more than the number of years.
• In-depth knowledge of Python and experience with relevant machine learning libraries.
• You’ve built LLM applications and run them in production.
• Solid experience with agent frameworks such as Lang Graph and Lang Chain, tool calling, MCP or similar orchestration. Our entire product is built around this. Experience with only a simple…