Nabaraj Subedi

M.S. in Computer Science @ University of Wyoming (2025–2027)

Graduate Research Assistant focused on Multimodal LLMs and RAG systems, building enterprise-grade conversational AI for transportation and civil engineering domains.

View Projects Download Resume

Contact: nsubedi1@uwyo.edu · +1 (307) 357-6341

Nabaraj Subedi

About Me

I’m Nabaraj Subedi, a Graduate Research Assistant at the University of Wyoming. I work on multimodal LLMs and retrieval-augmented generation (RAG), with a focus on building reliable, cost-efficient, and grounded enterprise chatbots—especially for transportation and civil engineering workflows.

Education

University of Wyoming

M.S. in Computer Science · 2025–2027

Relevant Courses: Intro to LLM, Machine Learning & Data Mining

Institute of Engineering, Tribhuvan University

B.E. in Electronics, Communication & Information Engineering · 2020–2024

Work Experience

Graduate Research Assistant

Multimodal LLMRAGEvaluation

University of Wyoming · Aug 2025 – Present

  • Research on multimodal LLMs and RAG systems; optimize cost–efficiency, accuracy, and groundedness.
  • Build evaluation pipelines using cloud tools, clustering, and validation workflows for state-level (WYDOT) conversational AI.

Junior Machine Learning Engineer

OpenAILangChainLangGraph

PalmMind Technology · Jul 2024 – Aug 2024

  • Built scalable RAG chatbots for EV dealers and insurance clients using orchestrator–worker routing and parallelization.
  • Improved retrieval with web scraping, OCR (Tesseract), and Redis caching for faster, context-aware responses.

Teaching Assistant

TeachingSystemsData Mining

Pashchimanchal Campus, Tribhuvan University · Sep 2024 – Jul 2025

  • Taught C programming, OOAD, Operating Systems, and Data Mining.
  • Designed labs, guided projects, and provided detailed feedback to improve practical programming skills.

Research Interests

Primary Interests

  • Multimodal LLMs and VLMs
  • LLM fine-tuning, evaluation, and RAG optimization
  • Applied AI for transportation and civil engineering

Fields of Interest

  • LLM
  • Multimodal AI
  • Data Mining
  • NLP
  • Computer Vision
  • Autonomous Systems

Projects

WYDOT Multimodal Chatbot

Multimodal RAGGemini 2.5Evaluation

Research Project · University of Wyoming

  • Deployed a multimodal RAG chatbot for images/audio/video/PDFs using fine-tuned Gemini 2.5 Flash/Pro with self-validation and multi-hop reasoning.
  • Processed 1,656+ WYDOT documents using LlamaParse, Unstructured, PyMuPDF, and Qwen2.5 captioning; performed clustering for similarity/versioning.
  • Built a high-quality Q&A dataset and fine-tuned multimodal models for improved precision, groundedness, and conversational efficiency.

Citi Bike History Data Analysis

BigQueryPythonML Pipelines

Personal Project

  • Analyzed 35M+ Citi Bike trips with full data engineering: ingestion, cleaning, feature engineering, anomaly detection.
  • Built analytics/ML pipelines (Random Forest, clustering, KDE, Sankey, community detection) to extract behavior, weather impacts, and network insights.

Banking Chatbot

OpenAITool CallingEmbeddings

Company Project

  • Researched embedding strategies, cost optimization, and token-efficient prompting to improve semantic accuracy while reducing inference cost.
  • Built agentic tool-calling chatbots enabling file retrieval, SQL querying, and task execution via structured tool pipelines.

Nepali Image Captioning

TransformerInception V3Full-Stack

Undergraduate Major Project

  • Generated paragraph-length Nepali captions using a Transformer + Inception V3; trained on 20,350 translated pairs + 800 cultural heritage images.
  • Compared Transformer vs LSTM baseline; integrated into a full-stack app (React frontend, Flask/Node backend).
  • Published work in Journal of Soft Computing Paradigm (2024).

Courses & Skills

Relevant Courses

  • Intro to LLM
  • Machine Learning & Data Mining

Tools & Platforms

  • Cloud/Compute: Google Cloud, ARCC Computing Cluster
  • LLMs/VLMs: Open-source LLMs & VLMs, Gemini fine-tuning

Technical Skills

  • Languages: Python, C, C++, Java, SQL
  • AI/ML: PyTorch, TensorFlow, Scikit-learn, Keras; CNNs, RNNs, Transformers; clustering (K-means, DBSCAN)
  • Data: Pandas, NumPy (plus visualization tools as needed)
  • Frameworks: LangChain, LangGraph, HuggingFace Transformers
  • Soft Skills: Communication, Team Collaboration, Time Management

Publications

Google Scholar ResearchGate
  1. Nepali Image Captioning: Generating Coherent Paragraph-Length Descriptions Using Transformer Journal of Soft Computing Paradigm, 6(1), 2024. DOI
  2. Drowsiness and Crash Detection Mobile Application for Vehicle’s Safety Journal of IoT in Social, Mobile, Analytics, and Cloud, 6(1), 2024. DOI