Nipun Agarwal

Nipun Agarwal is a graduate student in Communication Systems (specialization: Wireless Networking) at KTH Royal Institute of Technology, Sweden, with a strong foundation in RF engineering, signal processing, and AI-driven wireless systems. He combines hands-on device-characterisation experience from Micron Technology with a prolific research portfolio that spans 5G/6G RAN intelligence, UAV-assisted and NTN communications, federated learning for network management, virtualised network-function orchestration, and energy-efficient wireless designs.

Nipun’s engineering practice is grounded in rigorous measurement and modelling: at Micron, he led RF and microwave device characterisation (VNA calibration, power-compression and switching-speed analysis), guided lab operations, and contributed to multiple internal publications and patent filings. His research record includes peer-reviewed papers in major IEEE venues and accepted preprints on topics such as federated task offloading for UAV networks, deep-RL trajectory design for multi-UAV access, and ML/LLM methods for speech denoising, demonstrating an ability to translate advanced theory into reproducible simulation and experimental work.

Key strengths and profile highlights

• Interdisciplinary expertise spanning RF measurement, digital signal processing, machine learning, and network systems.

• Proven experimental skills with MATLAB/Simulink, software-defined radios (USRP/ADALM-Pluto), and lab equipment (VNAs, microwave test setups).

• Strong programming and data-science toolset: Python, C/C++, Pandas/NumPy, TensorFlow/Keras, Scikit-learn, Git, Docker.

• Demonstrated leadership in mentoring and teaching (TA roles, undergraduate project supervision) and active peer-review service for IEEE journals and conferences.

• Tangible impact: multiple journal/conference publications, accepted patents with Micron, and scholarships/awards recognizing academic excellence.

Research interests & career direction
Nipun is focused on advancing intelligent, resilient, and energy-efficient next-generation wireless networks: RAN intelligence (ML for control and orchestration), UAV/NTN integration, privacy-aware federated learning for network management, and experimental validation using SDRs and realistic propagation models. He is positioned to contribute to industry R&D or academic groups working at the intersection of wireless systems, RF engineering, and applied machine learning.