Research Engineer, GUIDE-AI

Are you passionate about advancing healthcare through innovative methods and cutting-edge technology? Do you have experience working across stakeholder groups to build and implement health AI solutions that directly impact clinical care? If so, Stanford University invites you to join GUIDE-AI within the Computational Medicine division as a Research Engineer to shape how AI is developed, evaluated, and deployed in healthcare.

GUIDE-AI (Guidance for the Use, Implementation, Development, and Evaluation of AI) is a Stanford Medicine initiative that spans Stanford University and Technology and Digital Solutions at Stanford Health Care. The key tenets under GUIDE-AI's mission are:

* Building and deploying healthcare AI solutions to address key opportunities to advance clinical care.

* Establishing evaluation and monitoring methods to assess deployed AI tools at Stanford Health Care and beyond.

* Disseminating actionable learnings to support high-value AI-augmented care for all.

As a Research Engineer for GUIDE-AI, you will lead technical development across a portfolio of healthcare AI projects, owning everything from data pipeline design to model evaluation and deployment. You will manage and/or work with technical teams across Stanford University, Stanford Health Care, and external partners to create scalable, collaboratively developed methods and tools. Potential projects may include developing innovative monitoring and evaluation methods, patient eligibility-matching tools, and generative and agentic systems to streamline clinical care delivery.

Beyond development, you will contribute to statistical analyses, prospective AI evaluation designs, and grant proposals, shaping study methodologies and supporting funding applications to advance GUIDE-AI's mission. Additionally, you will play a key role in mentoring trainees and students, maintaining well-documented code repositories, and driving long-term strategic initiatives for AI evaluation in healthcare.

Duties include:

* Conceptualize design, implement, and develop solutions for complex system/programs independently, such as developing and implement Python and SQL-based tools for AI evaluation.

* Engage in long-term strategic planning in collaboration with staff and project leadership.

* Work with a variety of users to gain information, and develop intra-system tradeoffs between different users, as necessary; interact with a diverse client base and outside vendor contacts.

* Document system builds and application configurations; maintain and update documentation as needed.

* Provide technical analysis, design, development, conversion, and implementation work.

* Work as a project leader, as needed, for projects of moderate complexity.

* Serve as a technical resource for grant applications.

* Contribute to statistical analyses, prospective AI evaluation designs, and grant proposals, shaping study methodologies, constructing statistical plans, and supporting funding applications to advance GUIDE-AI's mission

* Compare, evaluate, and implement new features and technologies, and integrate them into the computing environment.

* Follow team software development methodology.

* Mentor lower-level software developers, including trainees and students

* Actively collaborate with interdisciplinary groups to advance projects that drive both healthcare delivery and technical innovation.

DESIRED

QUALIFICATIONS:

* Proficiency in Python and SQL, with hands-on experience in data analysis, statistical modeling, and AI evaluation.

* Expertise in developing and implementing algorithms (e.g., neural networks, clustering, embedding models).

* Expertise in full-cycle application development, including design, testing, deployment, and optimization.

* Strong analytical and problem-solving skills, with the ability to define and address complex technical challenges.

* Effective communicator, able to collaborate with both technical and non-technical stakeholders.

* Proven ability to lead structured team development projects, ensuring efficient workflows and high-quality outcomes.

* Solid foundation in probability and statistics, including power analysis, hypothesis testing, and uncertainty quantification (e.g., constructing confidence intervals, bootstrapping).

* Experience in AI model evaluation, including performance metric selection, fairness and bias assessment, and data visualization.
* (Preferred) Direct collaboration with clinicians, evidenced by first-author publications in medical journals and/or co-development of clinically-facing tools.
* (Preferred)

Experience with real-world clinical data models and standards (e.g., FHIR, OMOP) is strongly preferred.
* (Preferred) Experience monitoring deployed AI tools, including performance drift detection, alerting, and iterative model updating.
* (Preferred)

Experience with prospective AI evaluations, including clinical trial design, real-world validation, and sample size estimation.

EDUCATION & EXPERIENCE (REQUIRED):

* Bachelor's degree and five years of relevant…