Cristian Vega

About

ML/NLP practitioner at Morf Health focused on unifying fragmented healthcare data by linking structured patient/encounter records with unstructured clinical notes. Has hands-on experience with transformer embeddings, vector databases, and domain fine-tuning, plus rigorous evaluation (precision/recall) and human-in-the-loop validation with clinical SMEs to make pipelines production-grade.

Key Strengths

• Built ML/NLP pipelines unifying structured patient data with unstructured clinical notes
• Production-focused validation: labeled benchmarks, precision/recall tuning, and threshold optimization
• Robust data linking with confidence scoring and cross-field consistency checks (IDs, timestamps, clinical context)
• Human-in-the-loop quality process with clinical SMEs to review edge cases and refine mappings
• Entity resolution across multi-system healthcare data using deterministic + probabilistic matching
• Designed scalable, maintainable Python data workflows with orchestration, testing, logging, monitoring, and config-driven design
• Improved search relevance and record linking using embeddings + vector DB similarity search and domain fine-tuning

Experience

Education

Skills

Languages