Functieomschrijving
Voor Rabobank zoeken wij een Data Scientist - GenAI / Chatbot. As a Data Scientist specialising in GenAI and chatbots, you help improve the quality and effectiveness of AI assistants. You work at the intersection of data, engineering and product, analysing chatbot behaviour, identifying weaknesses and turning your insights into practical improvements. Rather than building foundation models, you focus on what chatbots need to perform at their best: the right context, structure and capabilities.
You assess existing solutions against state-of-the-art approaches and help drive innovation in retrieval, generation, reasoning loops, tool calling and other GenAI capabilities. You investigate why a chatbot is not behaving as expected and determine what context or structure could help it succeed.
Your responsibilities
Your profile
You enjoy understanding and improving AI behaviour, not just debugging code. You think structurally, connect the dots and have a strong intuition for what good performance looks like.
Functie-eisen
Functie-wensen
Extra Informatie
You assess existing solutions against state-of-the-art approaches and help drive innovation in retrieval, generation, reasoning loops, tool calling and other GenAI capabilities. You investigate why a chatbot is not behaving as expected and determine what context or structure could help it succeed.
Your responsibilities
- Analyse chatbot outputs and identify improvements with the greatest potential impact.
- Diagnose gaps in context and determine what additional information AI agents need.
- Work with product managers and engineers to define criteria for evaluating agent performance.
- Collaborate with use-case teams and stakeholders to understand real-world scenarios and turn feedback into improvements.
- Improve retrieval mechanisms, data structuring and the onboarding of contextual sources.
- Design evaluation frameworks that support rapid, large-scale experimentation and continuous innovation.
- Translate functional requirements into actionable technical improvements.
Your profile
- You have a strong analytical mindset and are curious about why AI systems behave the way they do.
- You have a strong understanding of GenAI systems and experience with LLM-based applications.
- You have experience with retrieval-augmented systems.
- You understand prompts, context windows, retrieval and grounding.
- You can assess the quality of AI outputs and explain why results are effective or ineffective.
- You are familiar with API integrations, batch synchronisation, and structured and unstructured data.
- You work comfortably with engineers and can troubleshoot data flows and context ingestion issues.
- You can design evaluation frameworks that go beyond traditional machine-learning metrics.
- You understand functional context and user behaviour, and can work effectively across engineering and product teams.
- You communicate context gaps and reasoning clearly to engineers, product managers and stakeholders, and can develop clear proposals for improvement.
- Experience with human-in-the-loop evaluation is an advantage.
You enjoy understanding and improving AI behaviour, not just debugging code. You think structurally, connect the dots and have a strong intuition for what good performance looks like.
Functie-eisen
- Je kunt in het Engels werken.
- Je bent gedurende de volledige opdracht beschikbaar.
- Je kunt op donderdag op kantoor werken aan de Winthontlaan in Utrecht.
Functie-wensen
- Het is een pre als je ervaring hebt met human-in-the-loop-evaluatie.
Extra Informatie
- Aantal uur 36
- ZZP mogelijk? Nee
- Thuiswerken mogelijk? N.t.b.
- Startdatum zo spoedig mogelijk