AI Developer
Willmeng Construction Inc. — Phoenix, AZ (Full-time, Remote)
AI Developer and Researcher
Agam Chopra Ph.D.
I am an AI/ML researcher and developer specializing in multimodal learning, generative AI, computer vision, and scalable deep learning systems, with experience spanning biomedical imaging, representation learning, and applied AI. My future research focuses on developing biologically inspired, gradient-free ANN learning algorithms modeled on principles of brain development and learning.
- 6+ years AI research and engineering
- h-index 5 143 citations as of May 13, 2026
Experience
Research & Engineering
AI Consultant
J.S. Chopra & Associates — Remote, USA
- Built Python/SQL/PyTorch tools for audit automation, fraud review, anomaly detection, and model monitoring.
Doctoral Researcher
KurtLab, University of Washington — Seattle, WA
- Addressed limited access to expensive clinical biomarkers by designing novel controllable multimodal generative models for MRI to Tau-PET synthesis, including advanced vector quantization and information theory methods that improved quantitative performance metrics, interpretation, and clinician trust for Alzheimer's imaging research and technology adoption.
- Solved reproducibility and scale bottlenecks in 3D medical AI by building efficient PyTorch/CUDA preprocessing, training, and evaluation libraries; enabled experimentation at scale across Linux and HPC environments.
- Led model development across tumor synthesis, inpainting, classification, survival prediction, and registration workloads; achieved top placements in BraTS challenges from 2022 to 2024.
- Collaborated with Microsoft on clinically aligned LLM/VLM evaluation for complex medical datasets and with Amazon Robotics on 3D scene generation and damage estimation pipelines; translated research into applied AI workflows across healthcare and industrial environments.
- Secured 2 competitive research awards for AI imaging proposals, including an Amazon research grant and a University of Washington internal data science grant.
Graduate Teaching Assistant
University of Washington — Seattle, WA, USA
- Taught computational engineering through lectures, labs, office hours, and Python/C/C++ support for 200+ students studying numerical methods, optimization, scientific programming, and reproducible debugging.
Graduate Research Assistant
Stevens Institute of Technology — Hoboken, NJ
- Developed deep learning, preprocessing, and evaluation workflows for 4D accelerated-MRI registration, improving temporal consistency and alignment over classical baselines.
Full-Stack Software Engineer
Reindeer Shuttle Inc. — West Lafayette, IN, USA
- Built Python, SQL, JavaScript, and TypeScript tools for operations, demand forecasting, and business intelligence.
Education
Academic Training
Ph.D., Mechanical Engineering
Department of Mechanical Engineering, Biomedical AI and Computer Vision
University of Washington, Seattle, WA
M.S., Computer Science and Machine Learning
Stevens Institute of Technology, Hoboken, NJ
B.S., Physics
Purdue University, West Lafayette, IN
Research Publications
Research Record
- Partial Information Decomposition as a Multi-Contrast 3D MRI Selection Strategy for Resource-Constrained Deep Neural Network Training in Brain Tumor Segmentation. Chopra, A.; Kurt, M. Manuscript submitted to MICCAI 2026; preprint available at arXiv, 2026.
- SFL-Net: Source-Factorized Latent Representation Learning for Multi-Contrast MRI to Tau-PET Synthesis. Chopra, A.; Neher, C.; Ren, T.; Rivera, J. E. H.; Jahanian, H.; Kurt, M. Manuscript submitted to IEEE TMI; preprint available at arXiv, 2026.
- Here Comes the Explanation: A Shapley Perspective on Multi-contrast Medical Image Segmentation. Ren, T.; Rivera, J. E. H.; Chopra, A.; Oswal, H.; Pan, Y.; Ruzevick, J.; Kurt, M. arXiv, 2025.
- 3D Inception-based TransMorph: Pre- and Post-operative Multi-contrast MRI Registration in Brain Tumors. Abderezaei, J.; Pionteck, A.; Chopra, A.; Kurt, M. BrainLes / Springer LNCS, 2024.
- Re-DiffiNet: Modeling Discrepancies in Tumor Segmentation Using Diffusion Models. Ren, T.; Sharma, A.; Rivera, J. E. H.; Rebala, H.; Honey, E.; Chopra, A.; Ruzevick, J.; Kurt, M. arXiv, 2024.
- An Ensemble Approach for Brain Tumor Segmentation and Synthesis. Heras Rivera, J. E.; Chopra, A.; Ren, T.; Oswal, H.; Pan, Y.; Sordo, Z.; Walters, S. arXiv, 2024.
- An Optimization Framework for Processing and Transfer Learning for Brain Tumor Segmentation. Ren, T.; Honey, E.; Rebala, H.; Sharma, A.; Chopra, A.; Kurt, M. MICCAI Challenge / Springer, 2023.
- VIT-FNO; A Robust Model For Tracking Motion In 4d-mri. Chopra, A.; Pionteck, A.; Abderezaei, J.; Kurt, M. Summer Biomechanics, Bioengineering, and Biotransport Conference (SB3C), June 20–23, 2022, Eastern Shore, MD, USA.
- The Brain Tumor Sequence Registration (BraTS-Reg) Challenge: Establishing Correspondence Between Pre-operative and Follow-up MRI Scans of Diffuse Glioma Patients. Baheti, B.; Chakrabarty, S.; Akbari, H.; Bilello, M.; Wiestler, B.; Schwarting, J.; Chopra, A.; et al. arXiv, 2021.
Technical Skills
Technical Toolkit
Languages
- Python
- C
- C++
- SQL
- JavaScript
- TypeScript
- MATLAB
ML / AI
- PyTorch
- CUDA
- Transformers
- LLMs
- VLMs
- Latent Diffusion
- Reinforcement Learning
- Computer Vision
- Multimodal Learning
- Medical Imaging
- Self-supervised Learning
- Synthesis
- Classification
Systems
- Linux
- Git
- LaTeX
- Docker
- Singularity
- Azure
- HPC
- MLOps
- Data Pipelines
- Experimentation Frameworks
Strengths
- AI research
- Model development
- Production engineering
- Open-source tooling
- Technical mentoring
- Cross-functional collaboration