Job Details

About the Client
Our client is an innovative company at the intersection of healthcare and artificial intelligence. Founded by experts in health technology, clinical AI, and academia, they are building a leading AI training and validation platform. Their mission is to simplify data access for AI developers while ensuring the highest standards of data quality and patient safety. With an ambitious vision, they aim to become the go-to platform for responsible AI development in healthcare.

About the Role
Our client is seeking a skilled Data Scientist with expertise in Natural Language Processing (NLP) and Large Language Models (LLM) to work with structured and unstructured healthcare data. This role will focus on extracting meaningful insights from multimodal clinical datasets to support AI model development. The ideal candidate will collaborate with data scientists and technical teams to create high-quality, AI-ready datasets, driving innovation in patient care through data-driven solutions.

Responsibilities

• Develop NLP, LLM, and other ML-based pipelines to extract relevant information from text-based healthcare data and store it in scalable data models.
• Query complex source systems, including electronic medical records (EMRs) and clinical provider notes, to curate high-quality datasets for AI training and real-world evidence analysis.
• Lead data extraction, transformation, labeling, and quality control tasks to ensure accurate dataset development.
• Stay informed on advancements in applied NLP and generative AI, integrating cutting-edge methods into workflows where applicable.
• Design and validate multimodal data structures by integrating information from diverse healthcare sources.
• Develop clean, well-documented code to ensure compliance with HIPAA and other data privacy regulations.
• Troubleshoot data-related challenges and ensure the accuracy and integrity of all datasets.
• Collaborate with the technical product team to enhance data-related product offerings.
• Communicate complex findings and methodologies in a clear, accessible manner to both technical and non-technical audiences.

Requirements

• Advanced degree in Data Science, Biomedical Informatics, Computer Science, Biostatistics, or a related quantitative field. A bachelor's degree with significant experience may also be considered.
• Minimum of 2 years of experience in data science and machine learning, particularly in building pipelines for unstructured and semi-structured data extraction. Prior experience with healthcare data is highly desirable.
• Proficiency in Python and SQL, with experience using ML/NLP libraries such as PyTorch, TensorFlow, and Hugging Face.
• Familiarity with modern LLM applications and techniques.
• Strong technical writing, analytical, and communication skills.
• Excellent organizational abilities with the capacity to manage multiple projects in a dynamic environment.
• Experience in startup environments is a plus.

Technical Skills

• Experience with Git and version control.
• Understanding of encryption methods and data security.
• Experience querying enterprise data warehouses (EDWs) and working with electronic medical records (Epic, Cerner, Allscripts).
• Knowledge of medical ontologies and healthcare data standards.
• Experience handling imaging data formats like DICOM.
• Familiarity with AWS cloud infrastructure.
• Prior experience publishing research in peer-reviewed journals is a bonus.

Why Join?

• Fully remote role with flexible working hours.
• Comprehensive benefits, including healthcare, dental, vision, PTO, and more.
• Dedicated professional development days for skill enhancement.
• Collaborative and intellectually stimulating work environment.
• Balance between focused project time and team collaboration.
• Mission-driven company focused on improving patient care through AI innovation.
• Opportunity for occasional travel for in-person team collaboration.

If you're passionate about working with healthcare data and driving advancements in AI-driven patient care, we encourage you to apply!