Curriculum vitae
Updated September 29, 2026.
Research on representation learning, foundation models, language models, and survival analysis for oncology. Work spans health records, pathology reports and slides, radiology, and omics, with software for data integration, patient embeddings, information extraction, and outcome modeling.
Experience
Generative and Multimodal AI Research Scientist - Precision Oncology
H. Lee Moffitt Cancer Center & Research Institute · Tampa, Florida, USA
September 27, 2026 – Present
- Design, develop, and validate machine learning and deep learning methods for cancer diagnosis, prognosis, treatment response prediction, risk stratification, and decision support.
- Conduct research in multimodal learning and cross-modal representation learning, integrating health records, imaging, pathology, molecular and genomic profiles, and outcomes over time.
- Develop, adapt, fine-tune, and evaluate foundation models, large language models, vision-language models, and generative AI systems for oncology research.
- Design and compare embedding methods, data fusion architectures, survival models, and approaches for prognosis and treatment response prediction.
- Develop methods to extract, analyze, and reason over electronic health records, clinical documentation, pathology reports, and radiology reports.
7 more responsibilities
- Apply transformer architectures, representation learning, self-supervised learning, generative modeling, and foundation model adaptation to research questions in oncology.
- Build data and model pipelines that connect clinical, imaging, pathology, molecular, genomic, and longitudinal outcome data for training and evaluation.
- Implement and optimize model training, fine-tuning, evaluation, inference, and deployment using Linux, high-performance computing, distributed computing, and cloud platforms.
- Maintain data management, model validation, documentation, and computational reproducibility practices; use AI-assisted software development tools in research workflows.
- Work with clinicians, researchers, data scientists, and bioinformaticians to translate cancer research questions into models, analyses, and software.
- Contribute to research planning, execution, and project leadership; provide expertise in machine learning, multimodal AI, and foundation models, and mentor trainees as assigned.
- Prepare manuscripts, conference presentations, grant application contributions, and technical reports; support methodology development, intellectual property, and translational research.
Machine Learning Engineer I
H. Lee Moffitt Cancer Center & Research Institute · Department of Machine Learning · Tampa, Florida, USA
September 2025 – September 26, 2026
- Developed and maintained HONeYBEE software for generating patient embeddings from health records, pathology, radiology, and molecular data; released code and datasets through GitHub and Hugging Face.
- Developed CLEVER, a system that uses LLM agents to extract variables, patient timelines, and ICD codes from medical records while retaining document evidence and reasoning for review.
- Supported institution-scale deployment of CLEVER for record processing, variable extraction, and document quality review at Moffitt Cancer Center.
- Worked with pathology, oncology, epidemiology, and machine learning collaborators on model evaluation, cohort analysis, and publication of findings.
- Contributed to studies of pathology report extraction, survival modeling, radiomics, and transcription factor binding site prediction, and presented methods through workshops and research forums.
Graduate Research Assistant
University of South Florida · Tampa, Florida, USA
September 2022 – August 2025
Supervisors: Yasin Yilmaz, Ph.D., and Ghulam Rasool, Ph.D. Research collaboration with the Department of Machine Learning at Moffitt Cancer Center.
- Developed MINDS to aggregate and link oncology data from repositories into patient-centered datasets for machine learning.
- Developed HONeYBEE pipelines for preprocessing, foundation model inference, embedding generation, and integration of text, imaging, pathology, and omics data.
- Designed experiments for cancer classification, patient retrieval, cohort clustering, and survival prediction; compared modality combinations and fusion approaches.
- Contributed to SeNMo, EAGLE, and PARADIGM research on omics representations, attention, graph learning, and survival analysis.
- Collaborated on LLM methods for pathology report extraction, wrote manuscripts, and disseminated code, datasets, abstracts, and presentations.
Education
Ph.D. in Electrical Engineering
University of South Florida · Tampa, Florida, USA
August 2022 – August 2025
Dissertation: Embedding-Based Deep Learning Frameworks for Multimodal Oncology Data Integration.
Advisors: Yasin Yilmaz, Ph.D., and Ghulam Rasool, Ph.D.
B.S. in Electrical and Computer Engineering
Rowan University · Glassboro, New Jersey, USA
September 2018 – May 2022
June - July 2022: transition between degree programs following B.S. completion and before Ph.D. enrollment.
Teaching & workshops
June 12, 2026
Running Local LLMs Behind Institutional Firewalls: Hands-On Guide for Secure Clinical AI
Society for Imaging Informatics in Medicine Annual Meeting | Pittsburgh, Pennsylvania
Speaker and co-presenter, Learning Lab LL4022, with Ghulam Rasool and Asim Waqas. Instruction covered model selection, deployment behind institutional firewalls, and LLM workflows for imaging and pathology.
July 8, 2025
Scalable Multimodal AI in Oncology Using HONeYBEE: From Embeddings to Clinical Impact
Mayo Clinic AI Summit
Teaching assistant
February 23, 2024 and June 29, 2022
Building Transformer-based Natural Language Processing
NVIDIA Deep Learning Institute | North America | Virtual
Teaching assistant for two student workshops
February 22, 2020
Fundamentals of Deep Learning for Computer Vision
NVIDIA-sponsored workshop | Rutgers Business School, Rutgers University | New Jersey
Teaching assistant
Talks & presentations
2026
Multimodal AI for Precision Oncology: From Data Integration to CDS
Waqas A, Tripathi A. Stanford MedAI Group Exchange, session 155. Co-presenter
2026
Clinically Integrated Multi-Agent Artificial Intelligence System for Automated Extraction of Neuro-Oncology Biomarkers from Pathology Reports
Elzaafarany O, Tripathi A, Mokhtari S, Rasool G. Poster, Moffitt Scientific Symposium, Tampa, Florida. Coauthor
October 30, 2025
CLeVER Multi-Agent AI Orchestration for Temporal-Aware Clinical Variable Extraction from Unstructured Medical Records
Tripathi A, Waqas A, Rasool G. Dr. Robert Gillies Machine Learning Workshop in Cancer
March 22-27, 2025
AI-Driven Extraction of Key Clinical Data from Pathology Reports to Enhance Cancer Registries
Tripathi A, Waqas A, Venkatesan K, Ullah E, Schabath MB, Bui MM, Rasool G. USCAP 114th Annual Meeting, Boston, Massachusetts
March 20, 2025
Accelerate Cancer Research With AI-Driven Multimodal Data Integration
Tripathi A, Waqas A, Yilmaz Y, Rasool G. NVIDIA GTC 2025, Poster P74176
2024
Extraction of Discrete Information from Pathology Reports Using Local and Private LLMs
Rasool G, Tripathi A, Waqas A, Ullah E, Bui MM. Oral presentation, Digital Pathology Association, Pathology Visions. Coauthor
September 29, 2023
Advancing Cancer Research Through Integrated Multimodal Data Analysis: A Comprehensive Framework for Precision Oncology
Tripathi A, Waqas A, Yilmaz Y, Rasool G. USF AI+X Symposium
September 29, 2023
Pan-cancer Learning for Survival Prediction
Waqas A, Tripathi A, Mukund A, Stewart P, Naeini M, Rasool G. USF AI+X Symposium
Honors & awards
2024
Best Poster Award
Dr. Robert Gillies Machine Learning Workshop in Cancer
HONeYBEE: Enabling Scalable Multimodal AI in Oncology Through Foundation Model-Driven Embeddings. Award: $1,000.
December 12-13, 2024
Second place
Moffitt Cancer Center Bio-Data Club Hackathon
Project: Patient Data Vectors - An Efficient Cancer Research Framework.
2022-2025
Graduate Assistantship Award
University of South Florida
2018-2022
Dean's List
Rowan University
Peer review
Journal reviewer, 2025 - Present
Mentoring
Research collaboration with students and trainees.
Siddharth Sivaram
University of South Florida, Electrical Engineering · August 2025 - Present
Hanieh Ajami
University of South Florida, Computer Science · January 2025 - Present
Nikolas Koutsoubis
Moffitt Cancer Center, Department of Machine Learning · August 2024 - Present
Dominic Flack
Rochester Institute of Technology, Chester F. Carlson Center for Imaging Science · August 2024 - February 2025
Kavya Venkatesan
Moffitt Cancer Center, Department of Machine Learning · May 2023 - Present
Asim Waqas
Moffitt Cancer Center, Department of Machine Learning · August 2022 - August 2025
Memberships
IEEE Eta Kappa Nu (IEEE-HKN)
Member · April 16, 2024 - Present
Institute of Electrical and Electronics Engineers (IEEE)
Member
Technical skills
- Programming
- Modeling and inference
- Research methods
- Systems
Media coverage & acknowledgments
April 8, 2026
AI Tackles Pathology Report Complexity
Allerton J. The Pathologist
Interview with Marilyn Bui and Ghulam Rasool discussing the pathology extraction study led by Tripathi and colleagues.
January 18, 2026
Gilmer Valdes: Cancer Care Shouldn't Depend on Your ZIP Code
OncoDaily
Republishes a statement by Gilmer Valdes acknowledging Aakash Tripathi among the research collaborators whose work laid the groundwork for OncoBrain.