Yubraj Sigdel

I architect and ship production AI systems at Veel Inc. — recommendation, moderation, and pricing intelligence at scale — and research explainable AI and AI for low-resource languages, with a focus on Nepali NLP and open-source tooling.

About

I'm an AI Engineer & Team Lead at Veel Inc., where I design and deploy user-facing AI systems end to end — from research and system design through distributed, fault-tolerant microservice deployment. I lean on Kafka, gRPC, Redis, and GraphQL to keep recommendation, moderation, and pricing pipelines robust under partial failure at scale, while mentoring interns through the same path from ML fundamentals to production AI.

A recurring thread in my work is trust: I've built multi-signal AI content moderation systems that combine policy assessment, brand/product tagging, and authenticity scoring to catch misaligned content at platform scale, and I care about explainability — making sure a moderation or pricing decision a model makes can be traced back to a reason, not just a score.

My research interest is AI for low-resource languages, particularly Nepali — spanning OCR and handwritten-script digitization (ViT + NepBERT), sentence embeddings and semantic search (Nepali Sentence Transformers), and Romanized-to-Devanagari transliteration (mT5). I build in the open: frame extraction packages, MCP-based FFmpeg automation, and published models/datasets on Hugging Face. Open to conversations about applied GenAI, explainable ML, retrieval systems, and low-resource NLP.

Work & Research

Everything, in order

Nothing is hidden — the other track dims.

  1. Apr 2025 — now Role

    AI Engineer & Team Lead

    Veel Inc., On-site

    Architected a low-latency recommendation engine (Kafka, gRPC, Redis, GraphQL) and an event-sourced ETL/feature pipeline processing 500K+ records in near real time. Built a multi-signal content moderation system, a predictive pricing intelligence pipeline with MLOps retraining, and a semantic video retrieval platform on multimodal embeddings — while mentoring 8 interns.

    • Kafka
    • gRPC
    • Redis
    • GraphQL
    • MLOps
  2. 2024 Paper

    College Chatbot Using RASA

    KEC Journal of Science and Engineering, 2024

    A conversational chatbot built with RASA for automating student and administrative queries at Kathmandu Engineering College.

    • RASA
    • NLP
  3. May 2024 — Apr 2025 Role

    Junior AI Engineer / AI Trainee

    Vertex Special Technology (P.) Ltd., On-site

    Built GenAI-powered, RAG-based Gherkin test generation pipelines and automated DOM/XPath/Selenium workflows, cutting test execution time by 40%. Contributed image embeddings and CV pipelines to TelePlantDoctor.

    • RAG
    • Selenium
    • Computer Vision
  4. Jul 2024 — Sep 2024 Volunteer

    Contributor, AI for Women Farmers

    FruitPunch AI, Remote

    Annotated Nepali documents for OCR, NLP, and NER systems, and collaborated with OCR teams to strengthen Nepali text identification.

  5. 2025 Project

    DistantFrames

    Open-source Python package

    Intelligent frame extraction, scene-aware sampling, and automated video frame filtering for computer vision, dataset generation, and moderation pipelines.

    • Python
    • Computer Vision
    • Scene-aware sampling
  6. 2025 Project

    FFmpeg MCP

    Model Context Protocol server

    A production-ready MCP server that turns natural language instructions into executable FFmpeg workflows — trimming, resizing, subtitles, compression, and format conversion without hand-written commands.

    • MCP
    • FFmpeg
    • FastMCP
  7. 2024 Project

    Handwritten Document Conversion

    Open-source · GitHub

    A ViT + NepBERT two-stage architecture for handwritten Devanagari digitization, with YOLOv8 word-level detection, achieving a 9.08% Character Error Rate.

    • ViT
    • NepBERT
    • YOLOv8
    • RoBERTa
  8. 2024 Project

    Roman English to Nepali Transliteration

    mT5 · Hugging Face

    An end-to-end Romanized Nepali → Devanagari transliteration platform, with fine-tuned model and dataset published on Hugging Face.

    • mT5
    • Hugging Face
  9. Apr 2023 — Jul 2023 Internship

    AI/ML Intern

    FuseMachines Nepal, Hybrid

    Built a context-based Nepali News Recommendation System from scratch — scraping, embedding pipelines, and deployment — and trained a Nepali Sentence Transformer using translated STS datasets over NepaliBERT baseline embeddings.

    • Sentence Transformers
    • NepaliBERT

Publications

Peer-reviewed & preprints

  1. Yubraj Sigdel, Sujan Shrestha, Nabin Neupane. College Chatbot Using RASA. KEC Journal of Science and Engineering, vol. 8, no. 1, 2024. DOI Code

Full list on the academic portfolio →

Education

Degrees & schooling

  1. Bachelor's in Computer Engineering Kathmandu Engineering College, 2018–2023.

    82.41%
    • Minor Project: a computer vision system for face detection and recognition applied to criminal identification.
    • Major project: a Network Intrusion Detection System benchmarking multiple ML algorithms.

    Coursework Artificial Intelligence (AI), Mathematics, Applied Mathematics, Probability & Statistics, Numerical Methods, Big Data Technologies, Data Mining, Database Management System (DBMS), Operating Systems (OS), Data Structures & Algorithms (DSA), Theory of Computation (TOC), Object-Oriented Programming (OOP)

  2. High School Gorkha United Public School, 2016–2018.

More on the academic portfolio →

Also

Skills

  • AI / ML LLMs, Generative AI, RAG, NLP, Computer Vision, Recommendation Systems, Semantic Search, Predictive Modeling, Fine-Tuning, AI Content Moderation, Explainable AI (XAI), Low-Resource Language Modeling
  • Frameworks PyTorch, Hugging Face, LangChain, LlamaIndex, FastAPI, Sentence Transformers
  • Backend & systems Microservices, Kafka, Redis, GraphQL, gRPC, REST APIs, MCP, FFmpeg
  • Data & databases PostgreSQL, Milvus, ChromaDB, pgvector, Pandas, NumPy, Selenium
  • Languages & DevOps Python, SQL, Bash, Docker, AWS, Git/GitHub, CI/CD