Software & Technical Work

Selected machine learning, data science, and research-prototyping work across wireless networks, RF signal analysis, reinforcement learning, and optimization.

Technical Skills

• Programming: Python, MATLAB, Java, C#.
• Machine learning: PyTorch, TensorFlow, RLlib, Stable-Baselines3.
• Methods: reinforcement learning, deep learning, open-set recognition, continual learning, explainable AI, optimization, simulation-based evaluation.
• Tools: Git, LaTeX, Visual Studio, MS SQL Server.
• GitHub: github.com/Irshadmeer

Selected ML/Data Science Projects

• Energy-aware RAN optimization: machine-learning and real-network-data-driven methods for battery peak-shaving and price-aware radio access network control.
• RF signal classification: open-set and incremental-learning methods for recognizing known and unknown UAV signals from RF spectrogram data.
• Reinforcement learning for network control: hierarchical and multi-agent DRL methods for clustering, power control, mobility management, and soft handovers.
• Cell-free massive MIMO: adaptive antenna-control and resource-orchestration methods for energy-efficient O-RAN and cell-free systems.
• Explainable AI: feature-attribution and LLM-assisted analysis for interpreting learned network-control policies.