Data Scientist/ML (Agentic AI)

The role is within the Pharmaceuticals / Consumer Health industry. The position involves designing complex, multi-agent workflows and building the cognitive architecture of a Co-pilot for sales representatives, including Text-to-SQL routing and conversational interviews. The role offers flexibility for occasional travel to the Warsaw office and potential international travel to Germany, approximately once a quarter.

• Deep, practical experience with LangChain, LangGraph, or similar tools.
• Knowledge of integration concepts for TTS/STT systems.
• Strong Text-to-SQL skills for accurate data routing.
• Experience with validation of generative AI and RAG pipelines.
• Proficiency in Python, SQL, and Spark programming.

Nice to Haves:

• Familiarity with GitHub for version control.
• Experience with FastAPI for application development.
• Awareness of data solutions like Databricks.
• Understanding of Azure cloud services.

• Build complex agent routing and state management workflows using LangChain, LangGraph, or tools like n8n.
• Deploy advanced RAG systems and integrate TTS/STT pipelines for asynchronous "Human-AI interview" conversational flows.
• Map natural language to exact SQL parameters for business logic routing without guessing financial math.
• Design systemic validation pipelines (e.g., LLM-as-a-judge) to monitor hallucination rates and establish continuous improvement loops.
• Design systemic validation pipelines to evaluate RAG, intent classification, and transcription accuracy in Italian, including medical/pharmaceutical jargon.
• Optimize AI processes using prompt caching, context-window management, and configure fallback models to ensure seamless user experience.

The role requires occasional travel to the Warsaw office and potential international travel to Germany approximately once a quarter.