Throughout my career, I’ve worked at the intersection of engineering, physics, and machine learning, using data and algorithms to understand and interact with complex environments. My foundation comes from my Ph.D. work in granular physics and robotics, where I built custom hardware, designed high-throughput experiments, and developed analytical and simulation models to uncover new principles of locomotion and dynamic interaction with granular materials.

At Hi Fidelity Genetics, I led R&D efforts on sensor development and signal processing, transforming noisy, field-collected agricultural data into meaningful biological and environmental insights. I developed algorithms for impedance-based sensing, time-series analytics, and large-scale data visualization, and collaborated closely with agronomists, hardware engineers, and scientists to design experiments and interpret results.

In my current role, I work as an applied scientist and engineer on projects involving AI/ML, computer vision, and sensing for real-world systems. My recent work includes developing image-embedding pipelines for GPS-denied geolocation, and ML-based classification tools for image and video analytics. I enjoy solving open-ended problems that require a blend of physical intuition, algorithm design, and practical experimentation.

My portfolio reflects the range of environments I’ve worked in—from robotics and granular media to soil systems, root phenotyping, and environmental sensing. Across domains, I’m motivated by building systems that reveal structure in complex data and turning those insights into useful, real-world tools.

Please feel free to reach out at jjaguilar1@gmail.com.