About
I am a machine learning engineer specializing in computer vision and expanding into the broader horizons of large language models. My work bridges scientific computing, AI model development, and high-performance computing, built on a strong foundation in mathematics and computational methods.
My current area of research is combining AI methodologies with climate simulations to advance predictive accuracy and scalability.
Previously, I have:
- Led AI–HPC integration for Earth system modeling, embedding PyTorch models into the Community Earth System Model (CESM) using FTorch and deploying on NVIDIA GH200 and x86 architectures.
- Contributed open source enhancements to NCAR’s CESM to streamline AI integration.
- Built edge AI systems for public safety, integrating YOLO and fire detection models on NVIDIA Jetson devices.
- Developed AWS-based ML deployment infrastructure for community health and safety applications.
- Delivered tactical edge computer vision systems, optimizing AI inference pipelines for NVIDIA Xavier and advancing distributed training techniques.
I have authored technical publications and blog posts on hybrid AI–HPC workflows and containerized scientific models for heterogeneous architectures, and coauthored peer-reviewed research on neural iterative decoding for image compression.
With a Bachelor of Science in Mathematics, I combine theoretical rigor with practical engineering expertise to tackle AI-driven scientific and operational challenges.