Data Scientist (pharmaceutical launch planning) - September 2026
Summary
Build AI personas for pharma launch planning using knowledge graphs, RAG, and agentic workflows on Azure AI and Snowflake.
For one of our clients in the pharma industry we are looking for a Data Scientist (pharmaceutical launch planning)
Project name: Generate Insights from Hidden Knowledge (GIHK)
Project description:
The services are requested as part of the GIHK project; the Project has the goal of transforming knowledge graphs, RAG pipelines, and enterprise data into AI-driven personas that support pharmaceutical launch planning, customer experience, and evidence-based decision-making.
Background to the assignment:
The project requires a combination of strong software engineering skills with hands-on experience in LLM applications, agentic AI workflows, RAG, knowledge graphs, and scalable data platforms, because this expertise is not available internally the external contractor has a unique position compared to the client's internal project staff and provides significantly different services than the internal staff.
Tasks:
Key Technologies:
Required Qualifications:
Preferred Skills:
Nice to have:
Start: ASAP
Capacity: full-time, 40h/week
Duration: till end of February 2027
Location: remote
Hourly rate: 70-75 Euro/h
Project name: Generate Insights from Hidden Knowledge (GIHK)
Project description:
The services are requested as part of the GIHK project; the Project has the goal of transforming knowledge graphs, RAG pipelines, and enterprise data into AI-driven personas that support pharmaceutical launch planning, customer experience, and evidence-based decision-making.
Background to the assignment:
The project requires a combination of strong software engineering skills with hands-on experience in LLM applications, agentic AI workflows, RAG, knowledge graphs, and scalable data platforms, because this expertise is not available internally the external contractor has a unique position compared to the client's internal project staff and provides significantly different services than the internal staff.
Tasks:
- Technical Development of Synthetic AI persona using knowledge graphs, RAG, GraphRAG, chunking strategies, and enterprise data sources.
- Technical Design and implementation LLM-based features, agentic workflows, and AI-driven insight generation capabilities.
- Technical development and build of a scalable backend services, data pipelines, and integrations for AI/ML and persona-related use cases.
- Technical translation of business and product requirements into technical concepts, user stories, and working software.
- Test, refine, and optimize AI components for quality, performance, scalability, and reliability.
Key Technologies:
- Azure AI components, Azure OpenAI, Amazon Bedrock, OpenAI, Gemini, and Anthropic
- Agentic workflows, LangChain, LangFuse, Haystack, prompt orchestration, tracing, and evaluation
- RAG, GraphRAG, embeddings, vector search, semantic chunking, knowledge graphs
- Snowflake and enterprise data platforms for structured and semi-structured data
- Python, Rust, TypeScript, Node.js, FastAPI, Java, PostgreSQL
- Docker, Openshift, Kubernetes and CI/CD
Required Qualifications:
- Strong professional experience in software engineering, preferably with production-grade AI/ML or data-driven platforms.
- Hands-on experience with LLM applications, RAG pipelines, AI orchestration, and modern backend development.
- Good understanding of knowledge graphs, vector search, embeddings, chunking strategies, and unstructured data processing.
- Experience with cloud-native development, APIs, microservices, testing, CI/CD, and scalable system design.
- Ability to communicate complex technical topics clearly to both technical and non-technical stakeholders.
Preferred Skills:
- Experience with LangChain, LangFuse, agentic AI tooling, prompt tracing, evaluation, and observability.
- Experience with Azure AI components, Amazon Bedrock, Snowflake, ArangoDB, and multi-provider LLM orchestration.
- Experience with OCR, document intelligence, data extraction, or transformation of unstructured content into structured knowledge assets.
- Experience with document chunking strategies, semantic chunking, metadata enrichment, retrieval optimization, and improving context quality for RAG-based systems.
Nice to have:
- Experience in pharma, healthcare, biomedical data, launch planning, or customer experience use cases.
Start: ASAP
Capacity: full-time, 40h/week
Duration: till end of February 2027
Location: remote
Hourly rate: 70-75 Euro/h