Machine Learning Researcher
PhD, Systems and Industrial Engineering at University of Arizona
Minor in Computer Science
Research at CyPhyMan Lab and WEST Center on Water Resiliency Program
MSc, Data Science, Sapienza University of Rome
Research at Perception and Intelligence Lab (PINlab)
Advancing AI for intelligent, adaptive, and autonomous physical systems.
PhD researcher in machine learning at the University of Arizona, with over two years of industry experience. Research at the Cyber-Physical Manufacturing Systems Lab focuses on intelligent, self-correcting cyber-physical systems, combining predictive modeling, mathematical optimization, and reinforcement learning for decision-making and control. This work also explores foundation models and agentic AI for understanding physical dynamics, reasoning over multimodal data, and planning actions in real-world environments, with a primary focus on autonomous water treatment and collaborative research in additive manufacturing.
Earlier research at the Perception and Intelligence Lab, under the supervision of Dr. Fabio Galasso, involved developing novel transformer-based Multi-Style Networks for human pose forecasting to anticipate collisions in human–robot collaboration.
Industry experience spans end-to-end ML engineering, including propensity models integrated into an LLM-powered application for client behavioral segmentation and personalized recommendations at IBM, and multimodal deep learning models for spectroscopy-based drug detection at Lightsense Technology.
Developed and benchmarked multimodal deep learning models for drug detection from spectral sensor data. Evaluated robustness under noise and distribution shift and used predictive modeling to improve sensing configurations and detection sensitivity.
2025Built propensity models on more than 65M behavioral records, supported by statistical testing, feature ablation, and model benchmarking. Integrated predictions into an LLM-powered application for natural-language audience definition and model-driven decision support.
2026Developed PPO-based reinforcement learning policies for intelligent building energy control. Worked across the full ML lifecycle, including simulation, offline policy evaluation, AWS deployment, and production monitoring.
IndustryBuilt data pipelines and predictive systems for behavioral analytics, anomaly detection, and operational monitoring. Worked across ETL, feature engineering, predictive modeling, and production analytics.
Industry