Functie
AI Engineer – RAG Platform
Location: Utrecht
Working hours: 36 hours per week
Language: English, written and spoken
Working arrangement: Hybrid
About the role
As an AI Engineer – RAG Platform, you will improve the quality, accuracy and effectiveness of a production Retrieval-Augmented Generation (RAG) platform. You will work at the intersection of information retrieval, data science and software engineering, focusing on the performance of the RAG system itself.
You will investigate where and why the system underperforms, design experiments to test improvements, and translate your findings into measurable production outcomes. You will contribute throughout the improvement lifecycle, from failure analysis and hypothesis generation to evaluation, implementation and monitoring. Your work will draw on user feedback, retrieval metrics, evaluation datasets and production telemetry.
You will collaborate with software engineers, platform engineers, data scientists and product managers. This is a hands-on specialist role focused on retrieval systems, evaluation methodologies and applied AI.
What you’ll do
Improve retrieval performance, answer quality and the overall user experience through analysis, experimentation and optimization.
Investigate low-quality answers and identify retrieval or grounding issues.
Develop automated evaluation frameworks to measure retrieval quality, answer quality and user satisfaction.
Run large-scale experiments on chunking, embedding and retrieval strategies.
Analyze user interactions and system performance data in Databricks to identify opportunities for improvement.
Build feedback loops that identify weak responses and inform ongoing development.
Define and monitor quality metrics to measure improvements and identify regressions.
Turn analysis and experimentation into scalable, maintainable production solutions.
What you bring
A master’s degree or equivalent academic level in Data Science, Artificial Intelligence, Computer Science, Mathematics, Statistics or a related field.
At least 3 years of relevant experience in machine learning, applied AI or data science.
Demonstrable experience improving production-grade RAG systems or advanced retrieval-based AI solutions.
Experience designing evaluation methodologies and quality metrics.
A strong track record of turning analysis into automated production solutions.
Experience working with large datasets and complex distributed environments.
The ability to communicate findings and recommendations to technical and non-technical stakeholders.
A curious, analytical approach and a focus on measurable outcomes.
Technical skills
Retrieval-Augmented Generation (RAG) and large language models (LLMs)
Python and Databricks
Evaluation frameworks for generative AI systems
Embedding models and prompt optimization
Data pipelines and workflow automation
CI/CD practices and Azure
Nice to have
Experience fine-tuning language models.
Experience with ranking and retrieval systems.
Experience with AI observability and monitoring.
Experience working with large-scale production AI platforms.
Knowledge of synthetic evaluation datasets and benchmark creation.
Eisen
- English is mandatory
- The candidate must be available throughout the entire duration of the assignment
- All submitted candidates must have a valid passport or ID card and bring it to the interview and the start of the assignment
- The candidate may start only after successfully completing the pre-employment screening
- Midlance constructions are not allowed
- The candidate must have RAG experience
- The candidate must have experience with Large Language Models (LLMs)
- The candidate must have Python skills
- The candidate must have Databricks skills
- The candidate must have experience with evaluation frameworks for Gen
- AI systems
- The candidate must have experience with embedding models
- The candidate must have experience with prompt optimization
- The candidate must have experience with data pipelines and workflow automation
- The candidate must have experience with CI/CD practices
- The candidate must have experience with Azure
- The candidate must have a master's degree or equivalent academic level in Data Science, Artificial Intelligence, Computer Science, Mathematics, Statistics, or a related field
- The candidate must have at least 3 years of relevant experience in machine learning, applied AI, or data science
- The candidate must have demonstrable experience improving production-grade RAG systems or advanced retrieval-based AI solutions
- The candidate must have experience designing evaluation methodologies and quality metrics
- The candidate must have a strong track record of converting analyses into automated production solutions
- The candidate must have experience working with large datasets and complex distributed environments
- The candidate must be able to communicate findings and recommendations to both technical and non-technical stakeholders
- The candidate must be proficient in written and spoken English
Gunningscriteria
- Experience with fine-tuning language models is a nice-to-have
- Experience with ranking and retrieval systems is a nice-to-have
- Experience with AI observability and monitoring is a nice-to-have
- Experience working with large-scale production AI platforms is a nice-to-have
- Knowledge of synthetic evaluation datasets and benchmark creation is a nice-to-have
Extra informatie
Je sollicitatie dient uiterlijk 28 oktober 2026 om 09:00 uur door ons te zijn ingediend, voorzien van een motivatie (waarin wordt toegelicht hoe aan de eisen en gunningscriteria wordt voldaan) en twee referenties. Wij ontvangen je gegevens graag minimaal één werkdag vóór de sluitingsdatum.
