Abdullah Waqar Malik
NUST
· 2026
Email
abdullahwaqar29august@gmail.com
Phone
923129996929
GitHub
—
Academic
Program
Bachelors of Science in Computer Science
CGPA
3.57
Year
2026
Education
SEECS
Address
Wah cantt , Pakistan
DOB
—
Career
Current role
—
Target role
—
Skills
Deep Learning, Computer Vision, Reinforcement Learning, Neural Networks, AI-powered drone systems, Wildfire detection, Autonomous control, CNN architectures, Transfer learning, Edge deployment, Simulation-based experimentation, Mathematical models, Learning algorithms, Database performance, Backups and recoveries, Pandas, Matplotlib, TensorRT, SLAM, GPS tracking
Verbatim text
The exact text the LLM saw on the page (or the booklet text from the old import).
This is what powers semantic search.
Abdullah Waqar Malik Cell: 923129996929 | Email: abdullahwaqar29august@gmail.com LinkedIn: https://www.linkedin.com/in/abdullah-waqar-malik-26776524b/ Address: HOUSE NO. A-354, STREET#16, PRIME MINISTER WAHCOLONY, CANTT , Wah cantt , Pakistan PROFESSIONAL PROFILE Motivated Computer Science undergraduate with a strong focus on Deep Learning, Computer Vision, and Reinforcement Learning, and hands-on experience in research-driven projects. Skilled in designing and training neural networks for real-world applications, including AI-powered drone systems, wildfire detection, and autonomous control. Experienced with CNN architectures, transfer learning, edge deployment, and simulation-based experimentation. Demonstrated ability to work with complex mathematical models, optimize learning algorithms, and translate theory into practical implementations. Actively pursuing opportunities in AI research, intelligent systems, and applied machine learning. EDUCATION Bachelors of Science in Computer Science SEECS , Islamabad , 3.57 (4) INTERNSHIP EXPERIENCE Payactic SDS, H-13, Islamabad 01-Jun-2023 - 31-Aug-2023 Optimized database performance and ensured integrity through backups and recoveries. Documented database processes, procedures, and best practices. Generated reports and visualizations for analysis and decision-making using Pandas and Matplotlib. CSN Lab 01-Jun-2025 - 31-Aug-2025 Developed an AI-based wildfire detection pipeline optimized for deployment on edge devices (Jetson Nano). Worked with MODIS and VIIRS satellite datasets for wildfire monitoring. Applied TensorRT optimization to significantly improve model inference speed while maintaining competitive accuracy. Contributed to research output, including a co-authored paper on wildfire detection and segmentation. FINAL YEAR PROJECT AI-Powered Drone System for Early Wildfire Detection and Prevention Wildfires pose a significant threat to ecosystems, wildlife, and human settlements, often leading to devastating economic and environmental consequences. In recent years, wildfires have significantly impacted ecosystems and communities worldwide, with 2024 witnessing extensive fires across various regions. For instance, the 2024 South American wildfires affected countries like Bolivia, Brazil, Chile, Colombia, Ecuador, and Peru, resulting in approximately 346,112 wildfire hotspots and damaging or destroying about 85,866,867 hectares of land. Additionally, the 2025 California wildfires, including the Palisades Fire and Eaton Fire, burned thousands of acres, displaced thousands of residents, and led to substantial financial losses. Traditional fire detection methods, such as satellite imaging and ground-based sensors, often suffer from delays, limited real-time monitoring, and inefficiencies in covering large, remote forested areas. These shortcomings allow fires to grow rapidly before intervention, leading to catastrophic consequences. With climate change intensifying fire hazards, rising global temperatures, and prolonged drought conditions, there is an urgent need for a proactive, AI-powered solution to detect and prevent wildfires before they escalate into large-scale disasters. This FYDP aims to develop an AI-powered drone system for early wildfire detection and prevention by integrating computer vision, thermal imaging, and environmental sensor data. Additionally, autonomous drone navigation using SLAM and GPS tracking will ensure efficient fire monitoring and surveillance in large forested areas. The project will also focus on onboard AI deployment on edge devices for real-time inference, optimizing processing speed and minimizing response time. A real-time alert system will be developed to send early warning notifications with GPS coordinates to firefighting agencies and disaster response teams. Furthermore, a web/mobile dashboard will be created for remote monitoring, providing a user-friendly interface for real-time fire visualization and
AI enrichment
Abdullah Waqar Malik is a Computer Science undergraduate with a 3.57 CGPA, specializing in Deep Learning, Computer Vision, and Reinforcement Learning. He has practical experience in AI research, including developing an AI-powered drone system for wildfire detection and optimizing models for edge deployment.
Skills (AI)
["Deep Learning", "Computer Vision", "Reinforcement Learning", "CNN Architectures", "Transfer Learning", "Edge Deployment", "TensorRT", "Python", "Pandas", "Matplotlib", "SLAM", "Database Optimization", "AI Research"]
Status: ai_done