AI/ML Pipeline Design and Implementation –
- Lead the development of scalable and reproducible machine learning pipelines to support training, validation, and deployment of AI models using multimodal biomedical data.
- Design workflows that enable integration of EHR, imaging, and molecular datasets.
- Apply best practices in modular software design to ensure code maintainability and system extensibility.

Secure Software Architecture and Deployment –
- Architect secure infrastructure for deploying ML models using containerization (e.g., Docker, Kubernetes) and compatible with institutional computing environments.
- Ensure all software components meet cybersecurity and performance standards for research systems.
- Implement APIs and services to support integration of models into front-end tools or external systems.

Version Control, Documentation, and Testing – 
- Manage source control (e.g., Git), maintain continuous integration workflows, and implement automated testing pipelines.
- Create detailed technical documentation, including system architecture diagrams, model input/output specifications, and usage instructions.
- Contribute to reproducibility by using and maintaining MLOps tools (e.g., MLflow, Weights & Biases).

Cross-Functional Collaboration and Requirements Analysis –
- Collaborate with investigators, clinical researchers, and software engineers to define technical requirements and align model development with research objectives.
- Translate clinical and research needs into engineering solutions through iterative development and testing.
- Participate in team meetings, planning discussions, and user feedback sessions.

Mentorship and Optimization Support –
- Provide informal guidance to junior developers, students, or collaborators on ML coding practices and system design.
- Lead efforts to improve model performance, interpretability, and reliability through benchmarking and systematic evaluation.

Experience building and maintaining ML/AI pipelines for multimodal biomedical data
Proficiency in Python and deep learning frameworks such as PyTorch or TensorFlow
Familiarity with MLOps tools (e.g., MLflow, Weights & Biases)
Experience with Docker, Kubernetes, and cloud deployment
Knowledge of secure software design and research data governance
Experience working in interdisciplinary research teams
Strong technical documentation, version control, and testing skills
Ability to communicate technical decisions clearly and collaborate across functions
Additional technical certifications (e.g., AWS, Security+, etc.) may be encouraged but not required.