School of Medicine

Established in 1930, Duke University School of Medicine is the youngest of the nation's top medical schools. Ranked sixth among medical schools in the nation, the School takes pride in being an inclusive community of outstanding learners, investigators, clinicians, and staff where interdisciplinary collaboration is embraced and great ideas accelerate translation of fundamental scientific discoveries to improve human health locally and around the globe. Composed of more than 2,600 faculty physicians and researchers, nearly 2,000 students, and more than 6,200 staff, the Duke University School of Medicine along with the Duke University School of Nursing, and Duke University Health System comprise Duke Health, a world-class academic medical center. The Health System encompasses Duke University Hospital, Duke Regional Hospital, Duke Raleigh Hospital, Duke Health Integrated Practice, Duke Primary Care, Duke Home Care and Hospice, Duke Health and Wellness, and multiple affiliations.

The Duke Institute for Health Innovation (DIHI) catalyzes transformative innovations in health and healthcare through implementation of high-impact innovations, leadership development, and cultivation of a community of entrepreneurship. We bring innovative solutions to the most pressing challenges in health and healthcare through multidisciplinary teamwork across Duke University and Duke Health and by fostering collaborations with national and international thought leaders.

POSITION SUMMARY 

The AI / Machine Learning (ML) Engineer is responsible for designing, developing, and validating AI and ML products and systems within the scope of DIHI projects. This position will act as a liaison between product managers, data scientists, data engineers, and clinician users to determine the requirements for novel AI/ML models. This position will assist with curation and quality assurance of data across diverse clinical and operational data sources and will collaborate closely with data engineers and solution architects to ensure that machine learning models are effectively integrated into clinical care. This position will work closely with the DIHI Program Director to identify and pursue opportunities to leverage emerging statistics and machine learning methods and technologies to drive impact within Duke Health. This role will participate in activities throughout the machine learning product lifecycle, including initial design, development, internal and external validation, temporal and clinical validation, impact and outcomes analyses, updating, and maintenance. This role will utilize computing and statistics expertise to both develop AI-based solutions as well as assist in the design and conduct of evaluation studies to measure the effect of algorithms integrated into clinical care. Lastly, the engineer will help teach interns and trainees involved in DIHI workforce development programs.

The AI engineer will possess expertise in computer science, statistics and ML and generative AI to effectively develop solutions to improve care at Duke Health. This role will work closely with business unit leaders and compliance and regulatory support staff, and success carrying out responsibilities will be strengthened by strong interest in healthcare business, ethics, law, and policy. The AI Engineer will maintain comprehensive and contemporary knowledge of AI, ML and statistical methods and best practices, with a focus on development and validation of products and systems in the health setting. The AI Engineer reports directly to the DIHI Program Director.

The position assists and leads in performing the following functions:

1. Develops, evaluates, and implements AI and machine learning models
2. Develops and maintains AI solution evaluation, monitoring, maintenance, and oversight frameworks and structures for DIHI innovation projects
3. Engages diverse stakeholders in requirements gathering, technology design, development, and validation to build trust and accountability throughout product development lifecycle
4. Assists with the diffusion and dissemination of AI/ ML solutions and best practices

DUTIES AND RESPONSIBILITIES OF POSITION

• Development, validation, and implementation of AI and ML solutions – 45%
  • Works directly with data science lead, quantitative science trainees, and clinical trainees who are involved in model development and validation
  • Develops utilities and frameworks to standardize and enhance the development and validation of machine learning systems
  • Develops and updates monitoring systems to ensure that any implemented machine learning model continues to perform as specified
  • Reviews code and performs evaluations of previously built machine learning models before integration into technical infrastructure
  • Maintains contemporary knowledge of advances in AI and ML to ensure that emerging technologies are incorporated into DIHI development efforts
• Evaluation, monitoring, maintenance, and oversight of implemented machine learning systems– 35%
  • Works with clinical and operational leaders to define relevant outcome measures to demonstrate impact of AI integrated into care
  • Designs and conducts evaluations of AI and Generative AI products to identify strengths and weaknesses of model integrations and improve practices across DIHI
  • Collaborates with data engineering and solution architect team members to optimize technology infrastructure for rapid implementation of AI solutions
  • Defines model performance measures related to safety, efficacy, equity, and fairness to monitor and measure throughout the AI solution lifecycle as well as standard reporting practices to diverse stakeholders
  • Identifies opportunities to enhance implementation and maintenance of AI/ML systems, including automated reporting and notification to detect changes in model performance or unanticipated adverse events
  • Develops utilities to enable comparison of multiple model versions and rapid updating and evaluation of new model versions
• Stakeholder engagement and requirements gathering – 10%
  • Works directly with clinical and operational stakeholders to identify requirements, map clinical and operational workflows to identify opportunities for new technologies, and prototype solutions
  • Engages diverse stakeholders in design, validation, and evaluation of machine learning models to build trust and accountability in technologies that are built for integration into clinical practice
• Diffusion and dissemination of machine learning products – 10%
  • Participates in dissemination efforts via academic writing, conference presentations, and internal and external communications related to DIHI projects

Education:

Bachelor’s degree in computer science, statistics, mathematics, engineering, or related quantitative field is required. Candidates with master’s degree or relevant work experience in applied AI in healthcare will also be considered.

Knowledge, Skills, and Abilities:

• Strong background in computing and statistics with experience developing, evaluating, and implementing models
• Background in software development with experience in back-end and front-end development a plus
• Background in Python programming and in data management including Postgres or SQL
• Experience with clinical, EHR and/or administrative health data required.
• Experience working closely with clinicians and researchers across biomedical research disciplines developing solution for use in clinical care
• Excellent analytical and problem-solving ability
• Documenting and analyzing workflow and clinical processes
• Creating data solutions to support business processes

Preferred Qualifications

• Knowledge of software development, AI and machine learning, and technology infrastructure
• Experience in using LLMs and generative AI to develop software solutions in healthcare
• Development of frameworks to support development, validation, impact assessment, and maintenance of data-driven software applications

MINIMUM QUALIFICATIONS

Education

Refer to Job Description.

Duke is an Affirmative Action/Equal Opportunity Employer committed to providing employment opportunity without regard to an individual's age, color, disability, gender, gender expression, gender identity, genetic information, national origin, race, religion, sex, sexual orientation, or veteran status.

Duke aspires to create a community built on collaboration, innovation, creativity, and belonging. Our collective success depends on the robust exchange of ideas—an exchange that is best when the rich diversity of our perspectives, backgrounds, and experiences flourishes. To achieve this exchange, it is essential that all members of the community feel secure and welcome, that the contributions of all individuals are respected, and that all voices are heard. All members of our community have a responsibility to uphold these values.

Essential Physical Job Functions: Certain jobs at Duke University and Duke University Health System may include essentialjob functions that require specific physical and/or mental abilities. Additional information and provision for requests for reasonable accommodation will be provided by each hiring department.