Data Scientist

AI extraction pipelines Design, build, and maintain multi-stage document-extraction pipelines that combine deterministic rule-based logic with LLM-powered extraction, orchestrated as durable, resumable workflows. Integrate cloud document AI services and LLMs for classification and extraction. Own prompt engineering and structured-output design, ensuring outputs are strongly typed (Pydantic), validated, and traceable. Build evaluation frameworks, MLflow tracking, precision/recall/F1 measurement, model monitoring, drift detection, and production-grade AI document intelligence solutions.