AI Curation Data Scientist

This is a fully remote position, open to applicants in United States.

📋 Description

• Designing and evaluating software for data extraction and integration involving structured EHR content (XML, FHIR) as well as unstructured text content (attached documents)

• Organizing and assisting in the curation of data sets for model training purposes

• Tuning and training large language models (LLMs)

• Maintaining a comprehensive understanding of PHI/PII and de-identification policies and strategies at xCures, and implementing software solutions that adhere to these policies and strategies

• Developing and executing tests to assess the performance of data extraction and aggregation, aimed at enhancing efficiency, timeliness, and cost-effectiveness

• Implementing and managing code repositories

• Collaborating closely with the manager to explore methodologies, test hypotheses, and jointly implement innovative data science solutions

• Coordinating as necessary for a fully remote position

• Collaborating with Engineering and other departments to boost overall company efficiency and effectiveness

⛳️ Requirements

• Master's degree or equivalent experience in Computer Science, Software Engineering, Statistics, Biology, or a related field

• At least 5 years of practical experience in data science, machine learning, AI, data analysis, software development, and/or predictive analytics

• Proficient in applying generative AI and transformer models, particularly in training large language models (LLMs)

• Extensive experience in curating data sets for LLM training

• Significant hands-on coding experience with LLMs, embeddings models, sentence_transformers, and developing Python code for data extraction and/or classification tools

• Considerable prior work experience in parsing XML, JSON, and/or other complex data formats, ideally C-CDA health data

• Familiarity with TensorFlow, PyTorch, and/or scikit-learn

• Software development skills, including proficiency in Git

• Demonstrated efficiency and a cautious approach to utilizing LLM-assisted coding

• Experience in writing unit and integration tests for scientific/clinical data software, as well as in developing scientifically motivated data quality assessments

• A flexible, innovative, and proactive approach to delivering software and data products while fostering team collaboration

• A strong passion for the successful delivery of team projects

🏝️ Benefits

• Medical, Dental, Vision insurance

• 401k

• Equity options