As a Graduate Teaching Fellow at Texas A&M University, I had the privilege to play a role in enhancing the educational experience of undergraduate students in the Industrial and Systems Engineering department:ISEN 370: Production SystemsI facilitated a dynamic classroom environment for a cohort of 48 students, blending theoretical knowledge with practical case studies to deepen their understanding of key concepts in Production Systems. By integrating real-world examples and interactive discussions, I helped bridge the gap between academic concepts and industry practices, fostering a comprehensive learning experience.ISEN 350: Quality EngineeringIn this role, I designed and led engaging lab sessions that introduced undergraduate students to the fundamentals of Quality Engineering. Through well-structured case study sessions, I provided hands-on experience and practical insights into quality control and improvement techniques, reinforcing theoretical concepts and enhancing students’ problem-solving skills in the field.

As a Graduate Research Assistant at Texas A&M University, I led and contributed to various research projects focusing on machine learning (ML), computer vision, and advanced manufacturing.I spearheaded a cross-disciplinary effort to develop AI-driven autonomous decision-making systems for optimizing material recipes in on-demand manufacturing. I developed a machine learning model to predict porosity in the Directed Energy Deposition (DED) process using thermal images, achieving 90% accuracy and improving quality control in additive manufacturing.In healthcare, I led the design of an ML model using SwinUNETR-V2 to predict Hepatocellular Carcinoma (HCC) treatment outcomes from CT scans, achieving a 71% Dice score. This innovation led me to be named a finalist in the Data Analytics & Information Systems Competition (DAIS) at IISE 2024.In industrial anomaly detection, I developed AdalossCycleGAN, an enhanced CycleGAN model that achieved 92.9% anomaly localization on the CBT dataset, outperforming SimpleNet’s 89%. I implemented generative models, such as transformers and diffusion models, to detect anomalies across complex industrial images. I also innovated a graph Fourier analysis-based approach for defect detection in industrial images, achieving 99.4% classification accuracy. This work contributed to zero-defect manufacturing through explainable AI insights using SHAP.In prior work, I implemented Physics-Informed Neural Networks (PINNs) to predict thermal fields in 3D-printed materials, achieving a root mean squared error (RMSE) of 90 K. I also utilized machine learning on acoustic emission signals to identify microstructures in 3D-printed Ti-6Al-4V alloys, achieving 98% accuracy using MFCC-based features and logistic regression.My work showcases how advanced machine learning techniques can be applied to both industrial and healthcare challenges, driving innovation and improving process outcomes.

As a PhD Intern at Pacific Northwest National Lab (PNNL), I focused on applying machine learning (ML) and computer vision techniques to solve industrial challenges in welding and material analysis.I developed a machine learning model to predict resistance spot welding performance in aluminum-steel stacks by integrating process parameters with physics-based features. Using AutoML and combinatorial feature analysis, I optimized the model’s accuracy and reliability. This work advanced the understanding of welding processes and improved the precision of performance predictions, which is crucial for enhancing the quality of welded joints in manufacturing.In addition, I designed and implemented custom computer vision algorithms for segmenting microstructures and elemental deposits from material characterization images. By processing data from Scanning Electron Microscopy (SEM) and Electron Backscatter Diffraction (EBSD) scans, I created highly accurate segmentation models, improving the analysis of material structures and elemental distributions. These innovations contributed to more precise material assessments and advanced material characterization techniques.

• Worked in close collaboration with Prof. George Bennett as a Teaching assistant for 'Quality Engineering'.• Designed and conducted lab sessions for the ISEN 350 course covering the introduction to Quality Engineering for undergraduate students at TAMU.• Steered and guided the thinking process amongst students to develop a better understanding of Quality Engineering by carrying out 'Q&A', and industry-related case study sessions.

• Worked on analyzing how design and flow parameters influence the Flow Uniformity Index to improve the design of a catalytic converter like Diesel Oxidation Catalyst (DOC), Selective Catalytic Reduction (SCR), etc. • Developed CFD simulation models in ANSYS to determine optimal design parameters of the catalytic converters to achieve better flow characteristics that influence their efficiency under various conditions.

• Worked under Prof Satish Bukkapatnam at Texas A&M University (TAMU) during the summer break of 2017 as an undergraduate research intern in the Undergraduate Summer Research Grant - (USRG) program at TAMU. • Worked on the prediction of epileptic seizures from EEG signals using Balanced Random Forest Techniques and prediction of surface morphology changes during the Ultra-Precision Machining process using in-situ acoustic emission (AE) data.As a part of the USRG program, I participated in a Poster Presentation session and a 48hr Hackathon - Aggies Invent. My findings during the internship program have helped to publish an overview paper in on Prediction of Epileptic Seizures.

I was responsible for increasing the subscribers' list by 500 students, conducting an exam and other services for students offered by Cognitio. This internship helped me in developing my communication, management skills and strategies for better teamwork.