Nirajan Basnet
About
Namaste! I am Nirajan, a tech enthusiast. I have over two years of experience in Software Development, DevOps, and Artificial Intelligence. I am interested in Data Infrastructure, System Design, and Cybersecurity.
- Full Stack
- Machine Learning
- LLMs
- Data Infrastructure
- DevOps
MS in Computer Science, Aug 2024 - May 2026
Wichita State University
BE in Computer Engineering, Nov 2017 - Mar 2022
IOE, Pulchowk Campus, Tribhuvan University
Experience
- Designed automated backend workflows using Appium and Gemini LLM APIs to detect policy screens within Android apps; improved accuracy and reduced manual review overhead.
- Guided 100+ students in CS concepts; Facilitated office hours and evaluated projects, assignments, and quizzes.
- Built modular analysis tools involving API interactions, structured data processing, and scalable automation logic.
- Participated in the Hands-on Sessions on Linux System Administration, SIEM, and LogPoint architecture
- Built distributed, event-driven systems using Apache Kafka (CDC, Streams, Connectors), improving data reliability and reducing latency by 70%.
- Designed scalable schemas and improved MongoDB query performance by 20% through indexing and schema redesign.
- Built real-time IoT ingestion systems using AKS and Azure IoT Hub; achieved 99.2% service uptime.
- Led junior engineers’ onboarding and enforced high-standard code reviews to keep the codebase robust and scalable.
- Enhanced event processing throughput by 35% through Kafka Streams optimization.
- Identified and resolved performance bottlenecks in Linux-based Java/Python backend services, improving system stability.
- Gained hands-on experience with SIEM systems, ZFS, IVM, and secure filesystems; assisted in debugging production-level distributed services.
- Built a semi-supervised ML model to classify Nepali tweets into 8 sentiment categories with minimal labeled data.
- Developed and deployed a production-ready FastAPI service with optimized inference latency, powering a real-time COVID-19 discourse analysis dashboard.
- Conducted extensive research on implementing two-dimensional In-Video Advertising, emphasizing seamless integration of advertisements within platform videos to ensure a non-disruptive viewing experience.
Projects
Featured Publications
Billions of people across the globe have been using social media platforms in their local languages to voice their opinions about the various topics related to the COVID-19 pandemic. Several organizations, including the World Health Organization, have developed automated social media analysis tools that classify COVID-19-related tweets to various topics. However, these tools that help combat the pandemic are limited to very few languages, making several countries unable to take their benefit. While multi-lingual or low-resource language-specific tools are being developed, there is still a need to expand their coverage, such as for the Nepali language. In this paper, we identify the eight most common COVID-19 discussion topics among the Twitter community using the Nepali language, set up an online platform to automatically gather Nepali tweets containing the COVID-19-related keywords, classify the tweets into the eight topics, and visualize the results across the period in a web-based dashboard. We compare the performance of two state-of-the-art multi-lingual language models for Nepali tweet classification, one generic (mBERT) and the other Nepali language family-specific model (MuRIL). Our results show that the models’ relative performance depends on the data size, with MuRIL doing better for a larger dataset. The annotated data, models, and the web-based dashboard are open-sourced at https://github.com/naamiinepal/covid-tweet-classification.