Job
tzajni toj t-xnaq´tzb´il
AI Engineer
T-xilen t-xjel
Tqanil
- T-xilen aq´untl
- Toj tkyaqil amb´il
- najchaq
- Ja´lo
- Empresa
- Lefebvre Sdu
Tchik'b'ab'il
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 Medior AI Engineer to help shape how the intelligent core of that platform evolves.
HOW YOU'LL MOVE US FORWARD
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 useful answer. It does this with agents: specialised AI components that each handle part of the question and work together. In the legal domain, an answer can't just sound fluent. It has to be correct, and you must be able to see which source it comes from. This is not a pilot project: the platform runs in production and is used heavily every day.
As a medior, your focus is on building. You work independently, on challenges that come from customers and on challenges we spot ourselves. You break down a legal process, translate it into a technical process and work out how to best connect the pieces. Stuck on something? You say so, and your colleagues think along with you.
You build and improve the agents of GenIA-L and the way they work together.
You build and maintain our knowledge packages: for each legal article, an expert-validated set of commentary, case law, parliamentary history and practical interpretation. You also work on the pipelines that create these packages and keep them up to date.
You make quality measurable. With evaluation sets, observability and metrics, you show that answers, source attribution and reliability really improve. Not by gut feeling, but with evidence.
You build features for customers, such as analysing their own documents and new ways to search case law.
You work directly with editors and subject-matter experts, and check with them which parts of a legal question really matter.
You come up with and test ideas to make the product sharper or faster, and alternate AI experiments with back-end development.
WHAT WE'RE LOOKING FOR
You have a realistic view of LLMs. You see what they can do, but you also know their weak spots. You enjoy following new AI developments, but you don't just follow the herd: you stay critical. You think in a structured way and can break a complex problem into smaller pieces. You work independently, take initiative when things are unclear and are eager to learn fast. And you enjoy working with lawyers and editors, because they know what a good answer looks like.
• You have several years of experience in software or ML engineering. Depth in recent projects counts for more than years.
• You have good knowledge of Python and experience with relevant machine learning libraries.
• You have helped build an LLM application that runs in production. Not just prototypes, notebooks or courses.
• You have hands-on experience with agent frameworks such as LangGraph and LangChain, tool calling, MCP or comparable orchestration. Our entire product is built around this. Experience with only a simple search-and-answer (RAG) setup is not enough.
• You have measured the quality of an LLM system with evaluation sets or observability, and can give a concrete example. Experience with tools like MLflow and LiteLLM is a plus.
• You have back-end experience, including building REST APIs.
• You have experience in Kubernetes. Experience with Postgres is useful.
• Experience in a legal, tax or other knowledge-intensive domain is a plus.
WHAT YOU'RE SIGNING UP FOR
On Tuesdays and Thursdays, the team works together at the office. What colleagues value most here: mutual trust, room to experiment, and a team that helps each other out when someone gets stuck.
• A good base salary and a standard working week of 36 hours.
• An end-of-year bonus of 4% of your gross annual salary and variable profit sharing of up to 6% of your gross annual salary.
• 23 holidays and a personal choice budget of 12%, of which 8% is holiday allowance and 4% you can spend freely, for example on extra days off.
• A good pension scheme through PGB, including additional partner insurance.
• A travel allowance of €0.25 per kilometre or a public transport allowance, plus an attractive bike scheme. For employees who live less than 10 km or more than 60 km away, we have a tailored arrangement.
• Hybrid working: two days a week at the office in The Hague, on Tuesdays and Thursdays.
• Room to grow. In your field, in your role, in the organisation.
WANT TO KNOW MORE?
We'd love to tell you everything about the team and the role. Send us your CV and you'll hear from us within 2 working days. Any questions first? Text or call Nadine at 0628556265.
A reference check and a VOG (certificate of good behaviour) are part of the selection process.
Find more English Speaking Jobs in Netherlands on Arbeitnow
Source: Arbeitnow (https://www.arbeitnow.nl/jobs/companies/lefebvre-sdu/ai-engineer-den-haag-337711)
HOW YOU'LL MOVE US FORWARD
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 useful answer. It does this with agents: specialised AI components that each handle part of the question and work together. In the legal domain, an answer can't just sound fluent. It has to be correct, and you must be able to see which source it comes from. This is not a pilot project: the platform runs in production and is used heavily every day.
As a medior, your focus is on building. You work independently, on challenges that come from customers and on challenges we spot ourselves. You break down a legal process, translate it into a technical process and work out how to best connect the pieces. Stuck on something? You say so, and your colleagues think along with you.
You build and improve the agents of GenIA-L and the way they work together.
You build and maintain our knowledge packages: for each legal article, an expert-validated set of commentary, case law, parliamentary history and practical interpretation. You also work on the pipelines that create these packages and keep them up to date.
You make quality measurable. With evaluation sets, observability and metrics, you show that answers, source attribution and reliability really improve. Not by gut feeling, but with evidence.
You build features for customers, such as analysing their own documents and new ways to search case law.
You work directly with editors and subject-matter experts, and check with them which parts of a legal question really matter.
You come up with and test ideas to make the product sharper or faster, and alternate AI experiments with back-end development.
WHAT WE'RE LOOKING FOR
You have a realistic view of LLMs. You see what they can do, but you also know their weak spots. You enjoy following new AI developments, but you don't just follow the herd: you stay critical. You think in a structured way and can break a complex problem into smaller pieces. You work independently, take initiative when things are unclear and are eager to learn fast. And you enjoy working with lawyers and editors, because they know what a good answer looks like.
• You have several years of experience in software or ML engineering. Depth in recent projects counts for more than years.
• You have good knowledge of Python and experience with relevant machine learning libraries.
• You have helped build an LLM application that runs in production. Not just prototypes, notebooks or courses.
• You have hands-on experience with agent frameworks such as LangGraph and LangChain, tool calling, MCP or comparable orchestration. Our entire product is built around this. Experience with only a simple search-and-answer (RAG) setup is not enough.
• You have measured the quality of an LLM system with evaluation sets or observability, and can give a concrete example. Experience with tools like MLflow and LiteLLM is a plus.
• You have back-end experience, including building REST APIs.
• You have experience in Kubernetes. Experience with Postgres is useful.
• Experience in a legal, tax or other knowledge-intensive domain is a plus.
WHAT YOU'RE SIGNING UP FOR
On Tuesdays and Thursdays, the team works together at the office. What colleagues value most here: mutual trust, room to experiment, and a team that helps each other out when someone gets stuck.
• A good base salary and a standard working week of 36 hours.
• An end-of-year bonus of 4% of your gross annual salary and variable profit sharing of up to 6% of your gross annual salary.
• 23 holidays and a personal choice budget of 12%, of which 8% is holiday allowance and 4% you can spend freely, for example on extra days off.
• A good pension scheme through PGB, including additional partner insurance.
• A travel allowance of €0.25 per kilometre or a public transport allowance, plus an attractive bike scheme. For employees who live less than 10 km or more than 60 km away, we have a tailored arrangement.
• Hybrid working: two days a week at the office in The Hague, on Tuesdays and Thursdays.
• Room to grow. In your field, in your role, in the organisation.
WANT TO KNOW MORE?
We'd love to tell you everything about the team and the role. Send us your CV and you'll hear from us within 2 working days. Any questions first? Text or call Nadine at 0628556265.
A reference check and a VOG (certificate of good behaviour) are part of the selection process.
Find more English Speaking Jobs in Netherlands on Arbeitnow
Source: Arbeitnow (https://www.arbeitnow.nl/jobs/companies/lefebvre-sdu/ai-engineer-den-haag-337711)
A t-xilen lu tzajni toj jun t-xnaq´tzb´il. Q´onxa t-xjel toj t-xaq u´j te t-xe´chil.
t-xe´chil: Lefebvre Sdu
A t-xilen tzaj tqona Lefebvre Sdu.
