Data Scientist

Webologix Ltd/ INC; Utrecht; Presencial; EUR 65.000 - 85.000; Jornada completa

Descripción de la vacante

Webologix Ltd/ INC is seeking a data- and analytics-driven professional to evaluate chatbot outputs and identify improvements in Utrecht, Netherlands. You will partner with product managers and engineers to define evaluation criteria for agent performance and bridge gaps between use-case teams and engineering.

You will design scalable evaluation frameworks, improve retrieval and context onboarding, and translate complex requirements into concrete technical actions that enhance system reliability

Formación

• Strong analytical mindset and passion for understanding why AI systems behave as they do.
• Strong understanding of GenAI systems.
• Experience with LLM-based applications.
• Experience with retrieval-augmented systems.
• Strong understanding of prompts, context windows, retrieval, and grounding.
• Ability to evaluate output quality and explain why results are effective or ineffective.

Responsabilidades

• Analyse chatbot outputs to identify high-impact improvements.
• Diagnose context gaps and determine what information agents require.
• Define evaluation criteria with product managers and engineers.
• Collaborate with use-case teams to translate feedback into improvements.
• Improve retrieval, data structuring, and contextual onboarding.
• Design scalable evaluation frameworks for rapid experimentation and continuous innovation.
• Translate functional requirements into actionable technical improvements.

Conocimientos

Analytical mindset

GenAI systems

LLM applications

Retrieval-augmented systems

Prompts & grounding

Output evaluation

Herramientas

APIs

Data structuring

Engineering collaboration

Descripción del empleo

• Analyse chatbot outputs and identify the improvements with the greatest impact.
• Diagnose context gaps and determine what additional information agents require.
• Partner with product managers and engineers to define evaluation criteria for agent performance.
• Work directly with use-case teams and stakeholders to understand real-world scenarios and translate feedback into improvements.
• Improve retrieval mechanisms, data structuring, and onboarding of contextual sources.
• Design evaluation frameworks that enable rapid, large-scale experimentation and continuous innovation.
• Translate functional requirements into actionable technical improvements.

Your Talent:

• You bring a strong analytical mindset and a passion for understanding why AI systems behave the way they do;
• Strong understanding of GenAI systems.
• Experience with LLM-based applications.
• Experience with retrieval-augmented systems.
• Strong understanding of prompts, context windows, retrieval, and grounding.
• Ability to evaluate output quality and explain why results are effective or ineffective.

Technical Integration Skills:

• Familiarity with API integrations, batch synchronisation, and structured and unstructured data.
• Comfortable collaborating closely with engineers.
• Ability to troubleshoot data flow and context ingestion issues.

Analytical and Evaluative Mindset:

• Ability to design evaluation frameworks beyond traditional machine learning metrics.
• Understanding of functional context and user behaviour.
• Ability to operate effectively between engineering and product domains.
• Ability to explain context gaps and reasoning to engineers, product managers, and stakeholders.
• Ability to create clear and effective improvement proposals.