CV

Master's in Informatics

Technical University of Munich (TUM), Munich, Germany

• Major Coursework: Deep Learning, Machine Learning with Graphs, Deep Generative Models, Advanced NLP, Statistical Foundation of Learning, Quantum Computing, Computer Vision: Detection, Segmentation and Tracking

Bachelor’s Degree In Computer Engineering

Institute of Engineering, Pulchowk Campus, TU, Nepal

• Major Coursework: Theory of Computation, Data Structure and Algorithms, Operating System, Artificial Intelligence, Computer Organization and Architecture, Discrete Structure, Calculus, Data Mining, Probability and Statistics, Big Data
• Grade: 79.57% in aggregate

High School Education

Capital Higher Secondary School, Nepal

• Major Coursework: Physics, Chemistry, Mathematics, Computer Programming
• Grade: 87.2% in aggregate

Dhungel, P., Tandan, P., Bhusal, S., Neupane, S., & Shakya, S. (2020). An Efficient Video Compression Network. Proceedings of the IEEE, 1028-1034. Link to Paper

Data Scientist

E.ON Digital Technology, Munich, Germany

• My work involves performing data analysis and developing models on the data related to energy

Data Scientist

Naamche Inc, Kathmandu, Nepal

• I explored and analyzed large scale real-estate data. With the application of machine learning, I developed algorithms to assess the investment potential of real estate. I was involved in deploying such models with CI/CD pipelines.
• I also worked on various applications of Generative AI
• Reference: Mr. Saramsha Dotel

NLP Research & Development

Diyo.AI, Kathmandu, Nepal

• I worked on open domain and enterprise chatbots that could respond to queries in both English and Nepali.
• I also contributed to numerous Nepali NLP components such as Transliteration, Named Entity Recognition, Language detection
• For image-based queries, I also implemented object retrieval based on object detection and recognition.
• Reference: Dr. Bishesh Khanal

Computer Vision Research Intern

NAAMII, Kathmandu, Nepal.

• I worked on COVID-19 Lung CT Lesion Segmentation (3D) using CNN architectures like U-Net, DeepLabV3. I also participated in MICCAI endorsed competition on Lung Lesion Segmentation
• Reference: Dr. Bishesh Khanal

Data Science Intern

LIS, Lalitpur, Nepal

• I worked on assortment recommendations using online sentiments. I also explored and analyzed market trends using large-scale retail data.
• Reference: LIS human resource department

• Represented Nepal in the 47th International Physics Olympiad, Zurich

• Represented Nepal in ACM-ICPC, Dhaka regionals

• Winner: A day of code

• Winner: Locus Codejam

• Winner: National Level Programming Contest

• Second Place: DandyHacks organized by the University of Rochester via Devpost

• Second Place: Kathmandu University Coding Tournament

Video Compression Net, Undergraduate final year project

• It is a Deep Learning based video compression system that minimizes the number of bits required to encode video frames while also reducing distortion. The major objective of the project was to replace the conventional components in the pipeline of video compression with their neural network equivalents. The trained model equaled the compression ratio of the conventional system.
• I was involved in designing the architecture of CNN, combining the components, devising loss functions, and training the network end-to-end.

Covid-19 Emergency Chatbot

• A Viber bot, with more than 1100 subscribers, that caters to Covid-related queries in Nepali and English. With the addition of custom-made components like transliteration and NER, the chatbot was created using Rasa framework.

Population Simulation and Its Applications on Disease Spread

• A social-interaction simulation and modeling to visualize, analyze and predict the spread of disease. The simulation was carried out for Lalitpur district using the data from Central Bureau of Statistics, Nepal.

Lung Lesion Segmentation

• A CNN based model that operates on CT images(3D) and segments detect severity of lung lesions caused by SARS-CoV-2 infection. The project was carried out as a part of MICCAI endorsed competition on Lung Lesion Segmentation.

Drow-Z, Second Place in DandyHacks

• A CNN based model that operates on CT images(3D) and segments detect severity of lung lesions caused by SARS-CoV-2 infection. The project was carried out as a part of MICCAI endorsed competition on Lung Lesion Segmentation.

• Participated in the 3rd Nepal winter school of AI as teaching assistant in NLP

• Organized Locus Codejam

• Completed Deep Learning Specialization by Andrew Ng (Coursera)

• Participated in Hult prize 2019

• Organized and acted as a tutor on a competitive programming workshop