Data scientist CDD (F/H)
Core
Data scientist integrating large language models (LLMs) and building data pipelines to extract value for business needs in the financial guarantee sector.
Role type
Senior IC data scientist (LLMs & NLP)
Builds
production ML models | product features
Domain
Financial services / AI / NLP
Deliverable
production ML models
Required skills
Python, SQL, SAS, LLMs, prompt engineering, RAG, data pipeline development, NLP
Preferred skills
experience with document processing (PDFs), web scraping, data cleaning
Technologies
Python, SQL, SAS, LLMs, RAG
Responsibilities
Explore, evaluate, and integrate existing LLMs for specific business needs; develop prompt engineering expertise; design and implement data pipelines for heterogeneous sources (PDFs, reports, databases); maintain and evolve RAG tools; optimize data preparation processes.
Seniority
Mid-Senior, hands-on IC