Data Scientist - RAG & Document Intelligence

Craftware is a technology company of over 500 experts, empowering large organizations to solve complex business challenges with modern IT solutions - from sales systems and automation to data platforms and AI. We operate where technology must be reliable, secure, and scalable. We deliver end-to-end projects: from analysis and architecture through implementation to development and maintenance. We are a trusted partner of industry leaders such as Salesforce, Veeva, UiPath, and Databricks.

Model: remote Engagement: full-time

Data Scientist - AI Insight Generation (Senior)

Role summary

You’ll join an AI initiative at an international Consumer Health company focused on systematically generating meaningful, actionable business insights for its brands. You’ll combine structured data, business knowledge, analytical methods, and AI to uncover patterns, drivers, opportunities, and anomalies across brands, consumers, and markets. This isn’t about answering one-off questions. It’s about building repeatable, explainable, and scalable analytical solutions, where you consciously balance the flexibility of LLMs with deterministic analytical methods.

Responsibilities

• Generate insights: translate business questions into repeatable, explainable analytical approaches grounded in trusted data and knowledge, uncovering patterns, drivers, opportunities, and anomalies relevant to Consumer Health brands.
• Integrate data and knowledge: bring together structured data and knowledge from multiple sources, work with semantic data products, and use RAG and knowledge graphs to connect metrics, entities, concepts, and business context, giving AI-powered analysis the context it needs to reason consistently.
• Build analytical recipes and agent skills: turn successful analyses into reusable components with explicitly defined data, calculations, analytical steps, decision logic, and expected outputs, rather than relying on unconstrained LLM reasoning.
• Experiment with AI and analytics: systematically evaluate statistical and machine-learning techniques, LLMs, retrieval strategies, semantic models, knowledge graphs, prompts, and agentic workflows. Build evaluation datasets and define measures for accuracy, relevance, consistency, robustness, latency, and cost.
• Ensure quality, trust, and scale: verify that outputs are supported by the underlying data, that analytical logic behaves consistently, and that the same question produces reliable results across brands, markets, and time periods, keeping solutions explainable, reproducible, and efficient at enterprise scale.

Requirements

Must-have

• Strong Python skills with hands-on experience in machine learning and generative AI workflows, including production-grade code
• Strong experience with structured data and analytical methods: data exploration, statistical analysis, feature engineering, hypothesis testing, segmentation, trend and driver analysis, and translating business questions into robust analytical approaches
• Experience applying Generative AI and LLMs to analytical and knowledge-intensive use cases: prompt engineering, structured outputs, tool/function calling, context engineering, and RAG
• Ability to balance probabilistic AI techniques with deterministic analytical methods, choosing the right approach for the problem rather than defaulting to an LLM
• Understanding of data semantics and knowledge representation, with experience connecting business concepts, metrics, and entities through semantic models, ontologies, and/or knowledge graphs
• Experience with AI and analytical evaluation, defining and tracking quality metrics (e.g. RAGAS, DeepEval, Langfuse)
• Familiarity with multi-agent AI frameworks such as LangGraph, LangChain, or Pydantic AI
• Experience with vector databases (e.g. pgvector, Pinecone, Qdrant, Weaviate)
• Experience with Azure cloud services (Azure Apps, Containers, Storage, AI Search, AI Foundry) and/or AWS equivalents
• Experience with Databricks (Delta Lake, Unity Catalog, MLflow)
• Strong analytical mindset with a structured, experiment-driven approach to problem solving
• Fluent English, both written and spoken

Nice-to-have

• API and MCP development and integration skills (e.g. FastAPI, FastMCP)
• Experience applying analytics and AI to Consumer Health, FMCG/CPG, marketing, consumer insights, or brand performance use cases
• Experience building production-grade, end-to-end agentic AI solutions (full-stack development)
• Experience with Aegra (open-source, self-hosted Agent Protocol server for running AI agents)

We offer

• B2B contract (rate negotiated individually, up to 200 PLN net/h + VAT)
• Fully remote service delivery
• Broad range of projects (internal, international) - genuine variety of clients and tasks
• Budget for skills development and certifications as part of the collaboration
• Regular collaboration reviews and discussion of project scope
• Additional benefits available as part of the collaboration
• Networking and team-building events for project teams