Muhammad Talha

Academic

Career

Verbatim text

Muhammad Talha
Cell: 03039978773 |  Email: muhammadtalha25124789@gmail.com
LinkedIn: https://www.linkedin.com/in/muhammad-talha-44589926b?utm_source=share_via&utm_content=profile&utm_medium=member_android
Address: Appartement no. 603, Al-Madina Arcade , Street no. 2, h-13 , Islamabad , Pakistan
PROFESSIONAL PROFILE
Final-year Electrical Engineering student at NUST with strong hands-on experience in digital system design, RTL implementation,
and functional verification. Skilled in Verilog/SystemVerilog, circuit analysis, and simulation using industry-standard EDA tools.
Experienced in power and lighting systems through industrial internship exposure. A collaborative and detail-oriented team player
with a strong focus on safety, compliance with standards, and meeting project deadlines. Seeking opportunities to apply technical
expertise in digital design, embedded systems, and electrical engineering projects.
EDUCATION
Bachelor of Electrical Engineering
School of Electrical Engineering and Computer Science , Islamabad , 2.8 (2022 – 2026)
INTERNSHIP EXPERIENCE
Islamabad Carriage Factory
22-Aug-2022 - 09-Sep-2022
Collaborated with cross-functional teams to integrate electrical engineering solutions in multidisciplinary projects. Maintained
compliance with environmental and safety regulations while supporting power and lighting installations. Assisted in planning and
establishing delivery and installation schedules for machines, cables, and electrical fittings, ensuring timely execution of tasks and
adherence to project requirements.
FINAL YEAR PROJECT
AI-Based Multi-Disease Diagnostic System Using X-ray Images and Facial Analysis on FPGA
This project focuses on the development of an AI-based diagnostic system that utilizes deep learning techniques to detect multiple
diseases through the analysis of X-ray images and facial photographs. Convolutional Neural Networks (CNNs) are employed to
identify patterns associated with lung, cardiac, and other medical conditions from X-ray data, while facial image analysis is used to
extract indicators of additional health abnormalities. To achieve high-speed and energy-efficient processing, the trained deep learning
models are implemented on an FPGA platform, enabling hardware-accelerated inference with low power consumption. By fusing
information from multiple image modalities and leveraging FPGA-based acceleration, the system aims to provide rapid and accurate
disease detection, supporting early diagnosis in resource-constrained healthcare environments.
TECHNICAL EXPERTISE
Digital System Design & RTL Development
Experience in designing and implementing digital systems using Verilog and SystemVerilog, including RTL development, simulation,
and functional verification. Familiar with testbench creation, debugging, and timing analysis using industry-standard EDA tools.
FPGA Design & Hardware Acceleration
Hands-on experience with FPGA-based system implementation, synthesis, and testing. Knowledge of deploying computational
models on FPGA for high-speed and low-power applications using tools such as Quartus and ModelSim.
Embedded Systems & Programming
Skilled in embedded system development using C, C++, and Python. Experience with microcontrollers, sensor interfacing, and real-
time system behavior in academic and project-based environments.

AI enrichment