Senior LLM​/Machine Learning Engineer – Clinical Platforms

Position Summary

The Computational Health Informatics Program ((Use the "Apply for this Job" box below).) at Boston Children’s Hospital, a Harvard Medical School affiliate, is seeking an experienced Machine Learning Engineer to join the SMART Health IT team (). In this role, you will design, build, and deploy LLM pipelines that operate on real-world clinical data and support model validation and care delivery  will join the team that helped define national standards for healthcare data APIs and population-scale clinical data exchange, and that maintains widely adopted open-source platforms used by hospitals, researchers, and technology partners worldwide.

Your work will sit at the center of healthcare data innovation, translating modern AI methods into durable, production-grade tools used in clinical environments.

• Develop repeatable pipelines in Python using pandas, scikit-learn, and other statistical tools for data structuring, extraction and validation.
• Develop, analyze, and interpret large clinical text datasets using the latest natural language processing (NLP/LLM) methods to extract and validate insights to support clinical research and predictive modeling.
• Query and manage health datasets using SQL on AWS cloud
• Produce innovative solutions driven by exploratory data analysis from complex and high-dimensional datasets. Applies knowledge of statistics, machine learning, programming, data modeling, simulation, and advanced mathematics to recognize patterns, identify opportunities, pose questions, and make discoveries. Using a flexible, analytical approach to design, develop, and evaluate predictive models and advanced algorithms that lead to optimal value extraction from the data. Generates and tests hypotheses and analyzing and interpreting the results of experiments
• With minimal supervision and direction, completes assignments in the required timeframe; consistently adhering to and promoting standard operating procedures and best practices; maintaining and upgrading biomedical informatics tools, methods, and technologies; migrating data, documenting changes, and adjusting internal processes; resolving problems associated with assignments and seeking supervisor assistance when needed.
• Routinely leads, co-leads, or participates in biomedical informatics projects with other members from the BCH research community and external collaborators; setting goals and objectives for projects and demonstrating achievement of those goals and objectives; coordinating work activities with other stakeholders; contributing to the resulting presentations and/or publications.
• Trains staff and researchers; effectively tailoring presentations; developing, implementing, and maintaining knowledge management systems.
• Creates or contributes to a range of compelling communications (e.g., PowerPoint presentations, e-mails, memos, scientific presentations, and publications) that clearly deliver content; preparing communications appropriate for management and internal distributions.
• Presents at project meetings; effectively conveying progress and asserting point of view; constructively discussing issues and providing facts; building credibility and trust by asking thoughtful questions and actively listening; running productive project meetings that advance problem-solving.

• Bachelor's degree in a STEM;
  PhD, MD, MPH or MS preferred

• 2-3 years of experience in a professional work environment outside of academic setting.
• Demonstrated proficiency in Python and SQL and/or numpy libraries for natural language processing and validation.
• Strong foundation in statistics and applied quantitative methods.
• Familiarity with fast healthcare interoperability resources (FHIR) is a plus and can be learned on the job.
• Excellent communication, teamwork, and problem-solving skills.
• Excellent problem-solving ability, collaborative spirit, and scientific curiosity.