Data Scientist - AI and Experimentation

Company Overview

Pflegia is innovating within the healthcare sector by creating a smart job-matching platform that connects caregivers with healthcare employers. Their mission is to become Europe's premier platform for nursing job placements and to address the nursing shortage crisis.

Role Description

We seek a Data Scientist to leverage artificial intelligence pragmatically to enhance our product. This role intersects statistics, machine learning, and product management by building predictive analytical models, advancing large language model (LLM) and retrieval-augmented generation (RAG) features, and designing impactful experiments that optimize how supply meets demand on our platform. Your contributions extend beyond analysis to defining success metrics, delivering actionable insights, and ensuring measurable business outcomes.

Key Responsibilities

• Develop, verify, and deploy statistical and predictive models influencing pricing strategies, matching algorithms, and growth initiatives.
• Enhance our AI-driven product features, focusing on LLM capabilities and RAG techniques, and explore emergent AI technologies for product innovation.
• Manage AI feature dependability by crafting prompt and evaluation protocols, assessing output quality, and identifying regressions before users encounter issues.
• Translate ambiguous inquiries into hypothesis-driven A/B experiments that provide clear, data-based decision guidance.
• Analyze user funnels and journeys to identify friction points and optimize alignment between supply and demand.
• Collaborate with performance marketing to refine targeting practices, attribution models, and campaign effectiveness leveraging data insights.
• Establish relevant KPIs and build monitoring dashboards (using AWS QuickSight) to visualize business impact clearly.
• Maintain documentation and workflow transparency via Jira, coordinating across product, engineering, and marketing teams.
• Present evidence-based recommendations to stakeholders and oversee implementation to ensure impact realization.

Required Qualifications and Skills

• Strong passion and aptitude for data analysis, modeling, and data quality enhancement.
• In-depth statistical knowledge appropriate for diverse problem contexts, capable of justifying methodological choices.
• Proficient in Python (including pandas, scikit-learn, NumPy) and SQL, with experience solving practical business challenges.
• Hands-on application of machine learning and modern AI methods from conceptualization through deployment for real users.
• Experience working with LLMs and RAG pipelines in production or near-production environments, including tasks like prompting and output evaluation.
• Thorough understanding of A/B testing principles: sample size determination, significance testing, limitations, and appropriate use.
• Experience with performance marketing metrics such as Customer Acquisition Cost (CAC), Return on Ad Spend (ROAS), and attribution modeling.
• Project experience in domains including anomaly detection, trend analysis, marketing mix modeling, or multi-touch attribution.
• Background working within e-commerce, marketplaces, or platform businesses, ideally involving supply and demand modeling.
• Bonus: academic qualifications in quantitative fields such as mathematics, statistics, physics, or computer science.

Workplace Culture and Benefits

• Flat organizational structure with quick decision-making, complemented by an open and supportive work environment.
• Regular performance feedback and development conversations.
• Modern open-plan office located centrally in Berlin-Mitte, with flexibility to work from home.
• Friendly and cooperative team atmosphere.
• Complimentary beverages available on site.

Additional Information

Interested candidates are invited to submit their resume along with a brief description of a notable model or experiment they have recently implemented.