AI Engineer - Internship

Within our Client AI & Analytics team, CAIA, we have built our own multi-agent AI platform from scratch. The platform is used by commercial colleagues such as private bankers, relationship advisors and financial advisors. It supports them across a wide range of use cases, including client summaries, end-of-year reviews, meeting notes, investment proposal reviews and other daily advisory workflows. 

The platform combines the use of frontier AI models, agentic workflows and a growing set of capabilities across text, voice, memory and personalisation. We are moving beyond one-size-fits-all AI towards a platform that can better understand how different colleagues work, communicate and serve their clients. 

This internship focuses on GEPA-based self-optimisation. GEPA, or Genetic-Pareto, is a reflective optimisation framework that uses evaluation signals, traces and natural-language reflection to evolve prompts and other textual components of AI systems. It can be applied to prompts, instructions, agent configurations and broader compound AI systems.  

Within that theme, you will have room to shape your own direction. You might investigate how GEPA can optimise existing agents based on live interaction data, how user-level memory can be improved through implicit behavioural signals, or how smaller, more cost-efficient models can be tuned to approach the quality of frontier models. The common thread is clear: using GEPA to explore how our platform can learn from real usage and improve safely, measurably and continuously. 

That is what you will use your talents for as an AI Engineer Intern at Van Lanschot Kempen. You will research, design and prototype GEPA-based optimisation loops for our CAIA platform, exploring how interaction traces, feedback signals and evaluation metrics can help improve agents, prompts, memory and model selection safely, measurably and continuously. 

You also have the following tasks: 

• Use GEPA to optimise agent instructions, tool definitions and workflow configurations.  

• Explore GEPA-based personalisation of user memories and behavioural preferences.  

• Investigate GEPA tuning of smaller models to reduce costs without losing quality.  

• Build evaluation loops for measuring agent performance, reliability and user satisfaction.  

• Prototype self-optimising mechanisms for selected CAIA platform use cases. 

• Analyse live interaction data to identify patterns, friction points and improvement opportunities. 

• Speak with commercial colleagues to understand how they use AI in their daily work.  

Your talents

Curious, self-motivated and resourceful. This is how we can best describe you in the position of AI Engineer Intern. This internship is for someone who can be given a goal, think critically about how to approach it and independently find the best path forward. You do not need every step laid out for you: you enjoy exploring unfamiliar topics, testing different solutions, asking the right questions and turning ambiguity into progress. And all will be well if you also combine technical curiosity with a practical mindset and enjoy building things that real users can work with. 

 You also have: 

• You are currently completing or already have a degree in Computer Science, Artificial Intelligence, Data Science or a related technical field. 

• Experience building applications or prototypes with LLM APIs such as OpenAI, Anthropic or Gemini.  

• Familiarity with LLM concepts such as prompts, tool calling, structured outputs and evaluation.  

• Basic front-end experience with Angular, React or Vue.  

• Backend development experience in Python or C#. 

• Good mastery of English, both oral and written. 

Move ahead at Van Lanschot Kempen

Investing in a more future-oriented, sustainable, and data-driven way with various clients. Both nationally and internationally. With nearly 300 years of experience, we make this ambition a reality at Van Lanschot Kempen. We do this with some 2,300 colleagues in various fields of expertise.  

As part of the Client AI & Analytics team, you will work on AI solutions used by commercial colleagues across Van Lanschot Kempen. The team combines software engineering, data, analytics and generative AI to build practical tools for private bankers, relationship advisors and financial advisors. We work closely with users, move quickly from feedback to improvement and focus on responsible innovation with real business impact. 

An organisation's degree of innovation and agility also depends on the diversity of its workforce. Our differences make us stronger together. We promote an inclusive work environment where all colleagues feel at home. With us, you can be yourself. And we are proud of that. 

Curious about the stories of colleagues and how they experience working at Van Lanschot Kempen? Go to People & Projects and find out more! Or listen to our Podcast series to hear what our colleagues have to say.