NATNAEL DEJENE
Snellville,GA
Summary
Computer Science graduate with a Master of Science in Electrical and Computer Engineering from Kennesaw State University, with strong experience in data analytics, machine learning, deep learning, and AI model development. Skilled in Python, SQL, Power BI, TensorFlow, Pandas, NumPy, neural networks, and database querying. Experienced Data Analyst and AI Fellow with hands-on background in data cleaning, data modeling, dashboard development, data annotation, KPI reporting, and large dataset analysis. Proven ability to build machine learning solutions, develop automated reporting tools, analyze trends, and translate technical findings into actionable business insights. Strong academic foundation in artificial intelligence, neural networks, software-defined networking, FPGA design, and machine learning applications.
Skills
- Python
- Java
- Database querying using SQL
- Unix
- SDN using the RYU controller
- TensorFlow
- Deep learning
- Neural networks
- Pandas
- NumPy
Work History
Hand shake AI Fellow
HandShake
, Remote
08.2025 - Current
- Developed complex SQL queries and Python scripts to extract, clean, and model data, reducing manual reporting time.
- Built automated Power BI dashboards to track core performance metrics, giving leadership real-time visibility into model performance.
- Analyzed large datasets to identify bottlenecks and trends, translating technical findings into direct recommendations.
Data Analyst
Gozamin LLC
, Virginia
05.2024 - 08.2025
- Collected, cleaned, and transformed data using SQL to ensure data quality and consistency.
- Wrote SQL queries and Window Functions to analyze business data.
- Created interactive dashboards and reports in Power BI to visualize KPIs, trends, and business performance.
Data Analyst intern
Gozamin LLC
, Virginia
05.2023 - 05.2024
- Utilized various professional statistical techniques and maintained large databases to collect and analyze data from partners and customers.
- Completed data cleaning and data validation of existing spreadsheets to promote robust data management platform, resulting in accurate data analysis and entry.
- Monitored and controlled data upload, checking for successful data import and quality.
- Commissioned and decommissioned data sets under mentor supervision.
Education
Master of Science - Electrical and Computer Engineering
08.2024 - 05.2026
- Focus: Artificial Intelligence, Neural Networks, and Machine Learning Applications
- Relevant Coursework: Applications of Neural Networks, Circuit Analysis, Research Methodologies, Software Defined Networking (SDN), Field Programmable Gate Array (FPGA) Design
- 3.8 GPA
- Built and presented “Physics-Informed TCN Transformer with Localized P&O Refinement for Rapid Global MPPT Under Partial Shading” as a research poster for IEEE 54th Photovoltaic Specialists Conference (PVSC), focusing on AI-based maximum power point tracking for photovoltaic systems.
- Developed and evaluated a hybrid MPPT framework using TCN-Transformer prediction with localized Perturb & Observe refinement to improve global power tracking under partial shading conditions, analyzing performance through PV curve simulation, tracking efficiency, and power recovery metrics.
Bachelor of Science - Computer Science
05.2023
- Relevant Coursework: Data Structures, Software Engineering , Relational Database Querying
- Honors & Awards: Dean's List (Fall 2022, Spring 2023)
Projects
- Physics-Informed Deep Learning MPPT for Photovoltaic Systems
GitHub: https://github.com/nateej/DeepLearning_Zone_MPPT
Developed a hybrid deep learning-based Maximum Power Point Tracking system for photovoltaic systems under partial shading conditions. Built a Physics-Informed TCNformer model to predict the optimal MPP voltage zone from sparse 12-point PV curve scans, then applied local Perturb and Observe refinement to improve tracking accuracy. Implemented data preprocessing, model training, evaluation metrics, and visualization of true MPP, neural network predictions, refined MPPT points, and sparse sample locations. Co-authored research poster presented at the 54th IEEE Photovoltaic Specialists Conference (PVSC 54).
- Endangered Animal Classification
Developer (Team of 3)
https://github.com/nateej/deep-learning-dataset
Developed an AI-based image classification model using Python and TensorFlow. Employed transfer learning with a customized ResNet50 model to achieve 85% accuracy across 10 endangered animal classes.
- Crop Disease detection Developer
https://colab.research.google.com/drive/1mILcomEwM6ziN7CCF15NGYLE5asGcDaL?usp=sharing
Engineered a deep learning model leveraging the VGG19 architecture to classify plant diseases across 38 categories from a dataset of 87,867 images. Applied transfer learning, fine-tuning, and data augmentation techniques, achieving 99.4% test accuracy.
References
References available upon request.
Overview
3
3
years of professional experience
2
2
years of post-secondary education