CV

Summary

Machine Learning Engineer at Fusemachines, Kathmandu. Working on Multimodal LLMs, AI Agents, and Trustworthy AI.

Education

  • Bachelors in Computer Engineering
    2024
    Tribhuvan University, Institute of Engineering, Western Region Campus
    Courses: Software Engineering, Operating Systems, DSA, AI, DBMS, Big Data Technologies, Distributed Systems

Work Experience

  • Machine Learning Engineer
    2024-03-01 - Present
    Fusemachines, Nepal
    Built and delivered AI-driven systems, including document intelligence pipelines for financial workflows and research on multi-modal LLM-powered interview agent.
    • Built end-to-end document intelligence pipelines for financial workflows
    • Research on multi-modal LLM-powered interview agent for assisting hiring managers
    • Integrate ML solutions into production and communicate with technical and non-technical stakeholders
  • Teaching Assistant
    2026-03-01 - Present
    Fusemachines AI Fellowship
    Conducted sessions in a six-month AI fellowship program on deep learning fundamentals and real-world applications.
    • Mentored fellows through project ideation, implementation, and evaluation
    • Collaborated on session planning and enhancing curriculum and teaching materials

Skills

Machine Learning

  • Deep Learning
  • Transformers
  • Preference Optimization
  • RAG
  • AI Agents
  • Multimodal Learning
  • SFT
  • DPO

Frameworks

  • PyTorch
  • Hugging Face Transformers
  • Scikit-learn
  • OpenCV
  • ONNX

Programming

  • Python
  • C++
  • JavaScript
  • Bash
  • SQL

Systems & Infrastructure

  • Linux
  • Docker
  • AWS
  • HPC Environments
  • Vector and Graph Databases

Publications

  • Paddy Disease Detection and Classification Using Computer Vision Techniques
    2024
    arXiv:2412.05996
    Comparative study of object detection and classification for paddy disease identification using CNNs, Vision Transformers, and YOLO, plus a mobile app for real-time diagnosis.

Presentations

  • Applied AI
    2026
    Fusemachines AI Fellowship
    Kathmandu, Nepal
    Session on deep learning fundamentals and real-world AI applications for students and working professionals
  • Engineering AI Systems
    2026
    Fusemachines AI Fellowship
    Kathmandu, Nepal
    Session on engineering production AI systems, from model development to deployment and integration

Teaching

  • Deep Learning Fundamentals and Applications
    2026
    Fusemachines AI Fellowship
    Role: Teaching Assistant
    Six-month AI fellowship program for students and working professionals
  • Python and Machine Learning Mentorship
    2023
    Innovative Computer Engineering Society
    Role: Mentor (2023, 2024)
    Month-long Call for Enthusiast program guiding junior students in ML

Portfolio

  • Document Extraction Engine
    Portfolio
    End-to-end AI pipelines for information extraction from KYC, financial, and rental documents
  • Audio-LLM Research - Multimodal Interview System
    Portfolio
    Multimodal interview system using Qwen2-Audio with LoRA and DPO alignment
  • Conversational AI Chatbots
    Portfolio
    Seq2Seq dialogue models in PyTorch with GRU/LSTM attention and Transformers
  • YOLO Dataset Augmentation Tool
    Portfolio
    CLI tool for box-aware augmentation of YOLO object-detection datasets
  • Brain MRI Segmentation
    Portfolio
    UNet and UNet++ from scratch with Dice loss and IoU evaluation
  • Old Photo Restoration with GANs
    Portfolio
    Pix2Pix GAN (PatchGAN) restoration and inpainting of old photos on FFHQ-Small

Interests

  • Research Interests
    Multimodal LLMs and AI Agents, Trustworthy AI, Privacy Preserving, and Secure AI Systems