Muhammad Danish Khattak

PROFESSIONAL PROFILE AI and Computer Networking Engineer with hands-on experience in AI-driven optimization, wireless communication systems, and network performance analysis. Skilled in Python, MATLAB, Deep Learning, and simulation-based evaluation of 5G/6G, computer and IoT networks. EDUCATION BS Electrical Engineering School of Electrical Engineering & Computer Science (SEECS) , Islamabad , 3.76 (2026) INTERNSHIP EXPERIENCE Bravo Health, New York, USA 15-Jan-2025 - 08-Sep-2025 • Collaborate with the ML team to build predictive pricing and recommendation systems using LLMs (DeepSeek, Qwen, Claude) APIs and LoRA fine-tuning on large-scale healthcare datasets. • Develop scalable, low-latency pipelines with feature engineering on historical coverage and operational data to enhance model accuracy and relevance. TUKL Research and Development Lab (NUST) 15-May-2024 - 30-Aug-2024 • Contributed to the implementation of an EEG abnormality detection pipeline with advanced signal processing (band-pass filtering, ICA artifact removal) and statistical feature extraction (PSD, Hjorth parameters, entropy). • Co-Trained and evaluated supervised ML models (SVM, Random Forest) using k-fold cross-validation, optimizing for AUC and F1-score to improve diagnostic accuracy. Information Processing and Transmission Lab (IPT) | Research Assistant 30-Aug-2026 - 19-Jan-2026 • Pioneering novel network architectures and analyzing their performance using simulations and analytical techniques. • Conducting research aimed at tackling the evolving challenges in next-generation wireless networks. • Exploring and evaluating the feasibility of machine learning, particularly deep reinforcement learning, for optimizing future mobile networks. FINAL YEAR PROJECT Optimization of NOMA-Enabled Backscatter Communication Using Deep Reinforcement Learning in Diverse RIS-Aided Networks Designed and implemented an AI-driven framework for optimizing next-generation wireless communication systems. Developed a Python-based simulation environment for NOMA-enabled and RIS-assisted networks and applied deep reinforcement learning for dynamic power allocation and resource management. Evaluated system performance using key telecom metrics including throughput, energy efficiency, and reliability. The outcomes of this work were accepted for publication and presentation at leading IEEE wireless communication venues, demonstrating technical quality and real-world relevance. This project strengthened practical skills in wireless system modeling, optimization, and AI-enabled network design. TECHNICAL EXPERTISE Skills Languages: Python, C/C++, MATLAB, Verilog, LATEX Libraries & Frameworks: PyTorch, TensorFlow, scikit-learn, RLlib, TorchRL, NumPy, pandas, SciPy, OpenCV, Matplotlib, LangChain, Git, TensorBoard Design and Simulation Tools: ModelSim, Proteus,

AI and Computer Networking Engineer with hands-on experience in AI-driven optimization, wireless communication systems, and network performance analysis. Skilled in Python, MATLAB, Deep Learning, and simulation-based evaluation of 5G/6G, computer and IoT networks.