Professional Summary
Computer Engineering graduate with specialized expertise in applied machine learning, computer vision, and VLSI digital design. Proven track record of delivering innovative solutions from research conception through functional prototype development. Experience spans industry-leading research environments, including core AI research at Raytheon Technologies Research Center, autonomous systems development, and full-stack implementation of computer vision applications. Demonstrates exceptional capability in first principles analysis and systematic reduction of complex problems into modular, implementable solutions.
Professional Experience
Raytheon Technologies Research Center (RTRC)
Machine Learning Research Intern - AI Research Laboratory
Conducted advanced research in applied machine learning and computer vision within Raytheon's core research center, supporting all four business subsidiaries (Collins Aerospace, Pratt & Whitney, Raytheon Intelligence & Space, and Raytheon Missiles & Defense). Developed and implemented novel algorithms for computer vision applications in aerospace and defense contexts. Collaborated with senior research scientists on cutting-edge AI initiatives with direct application to next-generation aerospace systems.
Key Achievement
University of Michigan - Dearborn
Research Assistant, Machine Learning
Core team member for Michigan Dearborn Autonomous Shuttle development project, implementing end-to-end machine learning pipeline. Designed and executed comprehensive data collection protocols for autonomous vehicle training datasets. Developed convolutional neural network architectures for real-time sensory feedback processing and decision-making systems. Integrated computer vision algorithms with vehicle control systems for safe autonomous navigation.
University of Michigan - Dearborn
Teaching Assistant, Computer Methods
Created comprehensive solutions, evaluated student assessments, and provided detailed feedback for introductory C/C++ programming course. Mentored students in fundamental programming concepts and best practices.
Ford Motor Company
Intern, Functional Safety & Battery Architecture
Participated in ISO 26262 functional safety management protocols for electrical and electronic systems in next-generation vehicle platforms. Conducted competitive benchmarking analysis and technical evaluation for Battery Management Integrated Circuit (BMIC) selection study. Contributed to the architectural design of advanced battery electronics systems for electric and hybrid vehicle applications.
Education
Purdue University
Master of Science in Electrical & Computer Engineering
Focus: Signal & Image Processing, Deep Learning, Neural Networks
Key Coursework: Introduction to Deep Learning (ECE 59500), Neural Networks (ECE 62900),
Computer Vision on Embedded Systems (ECE 595), Deep Learning (ECE 69500), Boltzmann Law: Physics to ML (ECE 595)
University of Michigan, Dearborn
Bachelor of Science in Computer Engineering (with Distinction)
Specialization: Digital Design, Computer Vision, Autonomous Systems, VLSI Design
Research Role: Autonomous Vehicle Research Assistant
Featured Technical Projects
Smart Cat Door System
Advanced Computer Vision Pipeline
Architected end-to-end computer vision system combining real-time image processing, deep learning classification, and embedded hardware control. Implemented UNet architecture for precise pixel-level semantic segmentation of feline subjects. Developed custom CNN for robust animal identification and access control decision-making.
Deep-Fake Cat Generator (Remy)
Generative Adversarial Networks
Designed and implemented Wasserstein GAN with Gradient Penalty for high-fidelity synthetic image generation. Explored advanced techniques in generator-critic loss optimization and gradient penalty mechanisms for training stability. Demonstrated mastery of generative modeling principles.
ParkSmart iPhone Application
Full-Stack Computer Vision Solution
Led senior design team in developing comprehensive parking management system integrating computer vision, web backend, and mobile frontend. Implemented advanced CV techniques including homography matrices, perspective transforms, and edge detection for parking lot analysis.
VHDL Perceptron Implementation
Hardware Neural Networks
Designed Python-based MLP capable of learning geometric pattern recognition. Translated neural network architecture to optimized VHDL implementation with focus on combinational logic reduction. Demonstrated expertise in hardware-software co-design and FPGA-based neural network acceleration.
Technical Skills
Machine Learning & AI
- Deep Learning Frameworks: TensorFlow, PyTorch, Keras
- Neural Networks: CNNs, GANs, MLPs, UNet, ResNet
- Computer Vision: Object Detection, Semantic Segmentation
- Advanced: WGAN-GP, PCA, Backpropagation
- Model Optimization & Deployment
Programming & Development
- Expert: Python, C/C++, MATLAB, OpenCV
- Advanced: VHDL, Assembly, JavaScript, PHP
- Proficient: Java, R, LaTeX, Verilog, Bash
- Web: HTML/CSS, JSON, XML, SVG
- Version Control: Git, GitHub
Digital Design & Hardware
- VLSI Circuit Design, CMOS Logic Design
- FPGA Implementation, Hardware Description
- Digital Signal Processing, Embedded Systems
- Hardware-Software Co-design
- Real-time Systems
Systems & Platforms
- Cloud Computing: AWS, OpenVPN
- Web Development: LAMP Stack, Full-Stack
- Database Systems: SQL, Real-time Processing
- Operating Systems: Linux/Unix Administration
- Container Technologies