Data Scientist – NLP & Real World Evidence (RWE) - Remote

Veradigm Life Science

The Veradigm Network is well-positioned to address the unique needs of Life Sciences customers. By leveraging the Veradigm Network, research data and associated insights become both an output of care delivery, as well as additional knowledge to improve quality of care, a true virtuous cycle.

Our portfolio of solutions provides insights using real-world data directly sourced from the Veradigm Network. These solutions can help Life Sciences customers discover timely, actionable real-world evidence to improve patient experience and outcomes, and demonstrate how their products can benefit appropriate patient populations.

Job Summary

We are seeking a Data Scientist to join our Life Sciences Data Science team focused on extracting and leveraging insights from unstructured and semi-structured clinical data using Natural Language Processing (NLP) and Machine Learning (ML). This role is critical for transforming raw clinical text into NLP-enriched data to support Real World Evidence (RWE) studies and the Veradigm Network EHR (VNEHR) dataset.

The ideal candidate will have experience working with LLMs (preferably Azure OpenAI), a strong foundation in Python-based ML/NLP, SQL, and a demonstrated ability to work cross-functionally with clinicians, product, and operations teams to deliver high-accuracy, production-ready data science solutions.

Key Responsibilities

NLP & Machine Learning Development

• Design, develop, and deploy NLP and ML models using Python to extract insights from unstructured and semi-structured clinical text.
• Leverage Azure OpenAI and other LLM frameworks to enhance clinical data structuring and semantic understanding.

Clinical Collaboration & Validation

• Partner closely with clinical subject matter experts to validate models, ensuring high precision and accuracy in clinical contexts.
• Iterate on model development using feedback from real-world applications and clinician review.

Pipeline & Productionization

• Collaborate with Operations teams to design, implement, and optimize an end-to-end data science pipeline from R&D to production.
• Ensure data integrity, reproducibility, and compliance with healthcare regulations and best practices.

Data Analysis & Problem Solving

• Work with clients and stakeholders to identify key business problems and expected outcomes.
• Explore and assess internal and external data sources to extract relevant features and patterns.
• Communicate findings, methodologies, and actionable insights to both technical and non-technical audiences.

Qualifications

Required:

• Master’s degree in Data Science, Computer Science, Biomedical Informatics, or a related field.
• Proficiency in Python and SQL.
• Experience developing ML models, particularly with NLP techniques and libraries (spaCy, Scikit-learn, etc.).

Preferred:

• Experience with Azure OpenAI or other large language models.
• Familiarity with EMR systems, healthcare data standards (e.g. ICD-10, SNOMED).
• Exposure to cloud environments and big data tools (e.g., Snowflake, Azure, Spark).
• Demonstrated ability to work with clinical text and health data (e.g., EMRs).

Key Skills and Competencies

• Strong programming and data wrangling skills.
• Deep understanding of ML development lifecycles, from experimentation to deployment.
• Strong collaboration and communication skills, including the ability to work across technical and clinical teams.
• High attention to detail and strong analytical thinking.
• Understanding of HIPAA, data governance, and healthcare data privacy best practices.

Travel: Up to 1-2 times a year