I am Kaustubh Shah, a Machine Learning Enthusiast and researcher passionate about building intelligent systems that solve real-world problems. Currently pursuing my MS in Applied Machine Learning at the University of Maryland (3.9 GPA), I'm passionate about developing production-ready ML solutions, from predictive models to scalable deployment pipelines.

At the Precision Agriculture Lab, I build AI systems that forecast crop conditions using satellite imagery and deep learning, processing millions of geospatial records to deliver actionable insights for agricultural decision-making. My work spans the full ML lifecycle: from data engineering with PySpark and SQL to model development with PyTorch and TensorFlow, to deployment with Docker and AWS.

I am drawn to challenging problems at the intersection of computer vision, NLP, and distributed systems. Whether it's reducing fraud detection latency by 25%, improving video instance segmentation with temporal consistency mechanisms, or benchmarking LLM serving frameworks, I focus on measurable impact and production-grade solutions.

When I'm not training models or optimizing pipelines, you'll find me exploring the latest AI research, solving algorithmic challenges, or experimenting with new ML frameworks and techniques.

Currently: Graduating May 2026 and seeking ML Engineering and Data Science roles where I can apply deep learning, MLOps, and analytical problem-solving to drive business value.

Reach me at: kshah115@umd.edu