Senior Data Scientist – LLM / Clinical NLP @ Vecten
Core
Building and deploying LLM and transformer-based pipelines to extract structured clinical facts from unstructured medical notes for real-world evidence research.
Role type
Senior IC machine-learning engineer (clinical NLP)
Builds
Production-grade data extraction pipelines for US healthcare real-world evidence products
Domain
Healthcare / Clinical NLP / Real-World Evidence
Deliverable
production ML models
Required skills
LLM fine-tuning, transformer encoders, NER, text classification, relation extraction, RAG, Python, SQL, prompt engineering, model evaluation, error analysis
Preferred skills
EHR data experience, coding systems (ICD, CPT, RxNorm), PySpark, Databricks, AWS SageMaker, R, TypeScript
Technologies
Hugging Face Transformers, LoRA, PEFT, Claude, Cursor, MLflow, AWS, Jira
Responsibilities
Build extraction pipelines for clinical notes, evaluate models with gold-standard datasets, fine-tune and deploy models in production, collaborate with Medical and Product teams, present results to stakeholders