I’m a Computer Engineering student at NYU Abu Dhabi building practical tools at the intersection of sensing systems, probabilistic modeling, and scientific machine learning, shipping full-stack research software from data pipelines to deployment. My work spans NV-center quantum sensing platforms with nanosecond pulse control, probabilistic time-series modeling of MNAR sensor blackouts (state-dependent missingness + Kalman/EM pipelines), full-stack pharmacokinetic simulation apps, and ML pipelines for scientific time series, imaging, and vision. I care about uncertainty-aware inference, reproducibility, hardware–software synergy, and results that ship.
MNAR-aware state-space modeling for traffic sensors, treating blackout patterns as an informative observation channel and evaluating both blackout imputation and post-blackout forecasting.
I work across AI and experimental systems, building everything from deep learning models to real-world sensing platforms. On the quantum side, I developed a full-stack NV-center spectrometer with nanosecond pulse control and a PyQt6 GUI for code-free experiment execution. Recently, I’ve been leaning hard into Scientific ML for reliability and uncertainty: modeling information blackouts in MNAR sensor streams (state-dependent missingness) using state-space methods (Kalman filtering/RTS smoothing) and EM learning, and turning these ideas into clean, reproducible research code with robust evaluation. I also ship full-stack research tools, from PK/PD simulators to database-backed applications. I care about clarity, reproducibility, and building things that actually work.
🏅 Awarded Gold Medal and Best Integrated Human Practices (iGEM 2025): Recognized globally for impact in CDG-focused synthetic biology and integrating real-world feedback from patients, clinicians, and researchers to guide project design.
Led full-stack development of a PK/PD modeling platform for fitting, simulation, sharing, and reporting.
Engineered a full-stack NV-center quantum diamond spectrometer for sensing.
Produced emergency-response routing and recharge strategies for Koliwada using field surveys, GPS, and open mapping.
Led 15+ cross-department projects improving water access, Wi-Fi, laundry, and sustainability with feedback-driven systems.
MNAR-aware linear dynamical system for traffic sensors, modeling state-dependent outages; trained with EM and inferred with EKF/RTS, outperforms LOCF and MAR baselines.
PyQt6 interface for code-free Quantum Sensing experiments: protocol editor, YAML generation, live ODMR fitting, and device control.
Web app for PK/PD fitting and simulation with KPI extraction, dosing builder, VPCs, and PDF export.
Developed a MySQL-backed airline reservation system with a Flask web app, supporting flight search, ticket purchase, trip history, and staff dashboards on a normalized relational schema.
CycleGAN translating traditional textile motifs into contemporary designs with curated datasets.
Achieved 700×–2000× lossless compression of traffic matrices using feature-based sampling and matrix completion. Compression improves with dataset size and stabilizes for 10⁴–10⁵ vehicle entries. Implemented full encoding, decoding, and BCD optimization in NumPy/SciPy.
Trained a DCGAN in PyTorch to generate Fashion-MNIST clothing from latent vectors. Includes full adversarial pipeline, loss tracking, and checkpointed models.
Simulates ODMR spectra and experiments to accelerate NV-sensing development and validation.
Forecasts chaotic dynamics using fully connected feed-feedforward networks. Implements both direct and iterative methods, with custom training loops and RMSE evaluation across horizons.
Voice-navigated 3D campus tour of NYU Abu Dhabi built in Unity with teleportation, voice transcription, and interactive scene switching.
Designed and implemented a 14-bit signed microprocessor in VHDL with 16-instruction ISA, ALU, branching, and seven-segment FPGA display. Supports full simulation and hardware execution of custom binary programs.