The Client
The client is a healthcare analytics startup that uses NLP to draw insights from medical records and enables healthcare providers, pharmaceutical manufacturers, and insurers with insights for patient outcomes, risk factors and quality metrics to level up patient outcomes.
They are entering an exciting growth chapter, which requires adding an experienced data scientist to build, scale, and optimize our NLP and Machine Learning models to create the most effective and accurate models in the industry.
The Role
Requirements
- 2+ years of experience with NLP models to extract clinical entities (NER), assert their statuses (present, absent, positive, negative, etc.), and extract relationships between the entities such as dates related to adverse events
- Expertise with Python and PySpark
- Experience with training deep learning models with PyTorch, Hugging Face, or spaCy
- Willingness to annotate datasets for model training
- Capability to deploy models to the cloud or use data streaming tools such as Spark
- Strong communication skills
- Based in the United States
- BS in Computer Science, Mathematics, Statistics, or related field, MS or PhD preferred
Featured benefits
- Medical insurance
- Vision insurance
- Dental insurance
- 401(k)
- Tuition assistance