Sumit Aryal
Computer Engineer
About Me
I am a Machine Learning Engineer with a computer engineering foundation from Pulchowk Engineering Campus, IOE, Tribhuvan University. I turn ideas into AI apps people use, whether it's a chatbot that chats like a friend or a recommendation system that feels like it knows you.
I enjoy taking projects from writing Python code to Docker containers, deploying it on Kubernetes, and setting up CI/CD so it runs, and doing it all alongside product, design, and operations to solve real problems together.
I also aim to contribute to AI research by leveraging my expertise in Natural Language Processing, Computer Vision, and Large Language Models to create impactful solutions for real-world challenges.
Work Experience
AI Engineer
Root Level AIJanuary 2025 - Present
Kathmandu, Nepal
- Architected and deployed a Retrieval Augmented Generation conversational AI system following Agentic AI patterns.
- Optimized knowledge retrieval pipelines by implementing hybrid search (sparse + dense embeddings) and context-aware reranking, reducing hallucinations in LLM responses.
- Research, design and implementation of a two-tower recommendation system, replacing the traditional recommendation system, to increase user engagement.
Machine Learning Engineer
DoriITApril 2024 - December 2024
Kathmandu, Nepal
- Developed conversational agents using LLamaIndex, integrating OpenAI and Google Gemini APIs.
- Implemented CI/CD-driven RAG pipelines with FastAPI, Docker, and Kubernetes
- Mentored two interns on data preparation, model training, and evaluation for sentiment analysis and NER.
AI Fellow
FusemachinesJanuary 2023 - August 2023
Kathmandu, Nepal
- Completed intensive ML/DL curriculum, focusing on techniques like regression models, neural networks, and transformer-based architectures such as BERT.
- Built sentiment-analysis and text-classification models
- Applied image processing techniques, including detection and segmentation.
QA Trainee
Bajra TechnologiesSeptember 2022 - December 2022
Kathmandu, Nepal
- Developed and executed test cases for web applications, identifying and reporting over 50 bugs.
- Automated end-to-end testing using Cypress, reducing manual testing efforts by 15%.
- Conducted API and load testing using Postman and JMeter.
Education
Pulchowk Campus, IOE, Tribhuvan University
Lalitpur, Kathmandu
Bachelors in Computer Engineering
November 2019 - April 2024
Publications
C = Conference, J = Journal, S = In Submission, T = Thesis
BERT-Based Nepali Grammatical Error Detection and Correction Leveraging a New Corpus
Sumit Aryal, et al. (2024). Presented at IEEE INSPECT-2024, ABV-IIITM, Gwalior, India, December 07-08, 2024.
Nepali Grammar Correction
Sumit Aryal, et al. (2024). Undergraduate Thesis, Pulchowk Engineering Campus, Institute of Engineering, Tribhuvan University.
Projects
Nepali Grammatical Error Correction
As a part of major project thesis of my bachelor's degree, developed a pipeline utilizing BERT. Curated a large parallel corpus for Nepali Grammar Correction task. Developed a system which takes Nepali text as input, checks its grammar, and suggests corrections if necessary.
Chat with Multiple PDFs
Project implemented using Langchain and Huggingface Transformers for RAG framework. Users upload PDFs and ask questions. The PDF is segmented, converted to vectors, and stored. Questions are converted to embeddings, and a semantic search yields ranked results.
HTML Parser using LLM
Developed an API for extracting e-commerce attributes from HTML content. Uses `meta-llama/Meta-Llama-3-8B-Instruct` from Hugging Face's Inference API. Extracts attributes like name, price, description, and images from HTML.
Travel Recommendation System
Developed a travel recommendation web application that generates personalized itineraries for travelers to Nepal based on their preferences and budget using React, Django, Python, and Flask. Implemented collaborative filtering to enhance recommendations.
ML and DL Repository
Developed and maintained a repository of machine learning and deep learning algorithms, including CNN, Linear and Logistic Regression, Decision Trees, and advanced applications like Image Segmentation and Reconstruction.
8 Puzzle Visualizer
Implemented and visualized different algorithms, such as A*, BFS, DFS, IDDFS, and Greedy to solve the 8-puzzle problem using Python and Tkinter.
Bachiyo Game
Mario-like platformer game with various levels and sound effects created using C++ and SFML.
Image Compression
Compressed images using Huffman Tree Algorithm in C++.
Stadium Modeling
Modeled a stadium using Python, Pygame, and Blender.
Skills
Programming Languages
Data Science & Machine Learning
Applied ML Frameworks
Web Technologies
Cloud & DevOps
Specialized Areas
Mathematical & Statistical Tools
Soft Skills
Honors & Awards
Best Project Award
Pulchowk Campus, IOE
December 2024
Recognized for excellence in developing "Nepali Grammatical Error Detection and Correction System", an innovative NLP system that addresses the significant challenge of automated grammar correction in the Nepali language using BERT-based models and a novel corpus.
Certifications
Resume / CV
Having trouble viewing the resume? Download it or open it in a new tab using the buttons below.
Contact Me
Let's Connect
Feel free to reach out for collaborations, opportunities or just to say hello!
Send a Message
I'll get back to you as soon as possible.