Hello, I am

Sumit Aryal

Machine Learning Engineer

About Me

I am a machine learning practitioner and open-source contributor with experience in NLP, document AI, and end-to-end research and implementation of retrieval-augmented systems.

My recent work spans large vision-language models for structured data extraction, OCR pipelines for complex documents, agentic RAG systems for multi-turn support workflows, and scalable retrieval infrastructure built on Qdrant, FastAPI, and cloud-native tooling.

I am especially interested in bridging research and production, from low-resource language processing and BERT-based grammar correction to practical ML systems that deliver measurable quality, latency, and developer productivity gains.

Machine Learning
NLP
Python
Agentic RAG
FastAPI
Document AI
Qdrant

Work Experience

Software Engineer I, Machine Learning

Smart Data Solutions

November 2025 - Present

Eagan, MN, USA

  • Structured Data Extraction: Developed document processing pipelines using large vision-language models with custom processing logic for structured data extraction from multiple PDFs, using multimodal RAG techniques and vLLM-backed low-latency inference.
  • Advanced OCR Pipeline: Developing a scalable OCR system to replace legacy Tesseract-based workflows, enabling precise word-level and character-level bounding box extraction across complex document formats.
Python LVLMs vLLM RAG OCR

Machine Learning Engineer

Root Level AI

January 2025 - October 2025

Kathmandu, Nepal

  • Engineered an Agentic RAG system: Designed and studied retrieval-augmented generation for multi-turn support dialogs. Built a reproducible benchmark suite with synthetic and human-labeled queries, evaluated dense plus sparse hybrid retrieval with cross-encoder reranking and conversational memory, and tracked Recall@k, MRR, and end-to-end latency.
  • Retrieval Systems at Scale: Operated a multitenant, sharded Qdrant cluster with replication and write consistency. Studied shard key strategies and tenant-scoped payload indexes for fast filters.
Python FastAPI LlamaIndex Docker Kubernetes AWS Qdrant PostgreSQL Redis

Machine Learning Engineer

DoriIT

April 2024 - January 2025

Kathmandu, Nepal

  • LLM Integration: Created RAG assistants using OpenAI and Gemini and automated content generation tasks like summaries and descriptions, reducing manual operational work.
  • Text Analytics Pipeline: Developed sentiment analysis and named entity recognition systems using Hugging Face Transformers, and mentored two interns through dataset creation, BERT fine-tuning, and evaluation.
Python FastAPI LlamaIndex Docker OpenAI API Gemini API

Education

Pulchowk Campus, IOE, Tribhuvan University

Lalitpur, Nepal

Bachelors in Computer Engineering

November 2019 - April 2024

Publications

C = Conference, J = Journal, S = In Submission, T = Thesis

C.1

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.

IEEE Conference First Author
View Paper
T.1

Nepali Grammar Correction

Sumit Aryal, et al. (2024). Undergraduate thesis, Pulchowk Engineering Campus, Institute of Engineering, Tribhuvan University.

Thesis Best Project Award
View Thesis

Selected Open Source Contributions

2025

  • Qdrant Sharding: Enabled distributed Qdrant deployments, added configurable sharding and replication with write consistency controls in QdrantVectorStore, and introduced custom shard-key selection across CRUD flows. PR #19652.
  • Payload field indexes: Implemented payload_indexes support with index creation logic in both sync and async flows and added fixtures and tests. PR #19743.
  • Memory Component: Added missing synchronous wrapper for put_messages in the memory component to align sync and async interfaces. PR #19746.
Qdrant Integration Memory Testing

2025

  • Python Agents SDK example: Added a ready-to-run example that sets up an agent with local gpt-oss models, connects a filesystem MCP server, defines a custom weather tool, and streams agent responses. PR #14.
Agents MCP Python

Projects

Research Agent

Research agent with planning, search, reflection, and synthesis. Built around an async state machine that runs concurrent searches with adaptive concurrency and reflection cadence, honors budgets and deadlines, and synthesizes cited answers from normalized sources.

Python Pydantic asyncio Agentic Workflow

RAG Project

Retrieval pipeline with OCR ingest and hybrid vector search. Built as a FastAPI service backed by PostgreSQL and Qdrant, with Gemini OCR, structured chunking, dense plus sparse embeddings, and grounded answer generation with cited snippets.

FastAPI Qdrant PostgreSQL HuggingFace Gemini RAG

Nepali Grammatical Error Correction

As part of my bachelor thesis I built a BERT-based Nepali grammar correction (Nepali GEC) pipeline. I curated a large parallel corpus for the Nepali grammatical error correction task and implemented a system that ingests Nepali text, detects grammatical errors, and proposes context-aware corrections.

Python BERT PyTorch NLP HuggingFace Transformers

HTML Parser using LLM

Cleans raw HTML and extracts e-commerce attributes using an LLM in a site-agnostic way, producing CSS selectors and XPaths as structured JSON for downstream automation.

Python HuggingFace LLMs FastAPI

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.

React Django Python Flask Pandas

ML and DL Repository

Collection of machine learning and deep learning implementations spanning core algorithms, neural networks, and practical experiments used to build stronger fundamentals across NLP and computer vision workflows.

Python PyTorch TensorFlow

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.

Python Tkinter A* Algorithm BFS/DFS

Bachiyo Game

Mario-like platformer game with various levels and sound effects created using C++ and SFML.

C++ SFML Game Dev

Image Compression

Compressed images using Huffman Tree Algorithm in C++.

C++ Huffman Coding Algorithms

Stadium Modeling

Modeled a stadium using Python, Pygame, and Blender.

Python Pygame Blender 3D Modeling

Skills

Core Languages

Python Rust C/C++ Shell Scripting

ML/DL Stack

PyTorch HuggingFace Transformers Scikit-learn TensorFlow Pandas NumPy

Natural Language Processing

LlamaIndex LangChain/Graph Fine-tuning Agentic Workflow Text Analytics

ML Infrastructure & MLOps

Docker Kubernetes AWS (EC2, S3, Lambda, ECR) CI/CD Pipelines

Data Systems

Qdrant PostgreSQL SQLAlchemy DynamoDB Redis

API & Deployment

FastAPI RESTful Design Streamlit Serverless Architectures

Specializations

NLP RAG Low-Resource Language Processing Recommendation Systems Computer Vision

Soft Skills

Communication Problem Solving Teamwork Quick Learning Mentoring

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.

Department Honor Team Achievement

Certifications

Deep Learning Specialization

DeepLearning.AI

December 2023

View Certificate

Generative AI with Large Language Models

DeepLearning.AI

October 2023

View Certificate

Microdegree in Deep Learning

Fusemachines Inc

August 2023

View Certificate

Coding and Programming

Samsung

May 2023

View Certificate

Microdegree in Machine Learning

Fusemachines Inc

May 2023

View Certificate

Machine Learning Specialization

DeepLearning.AI

November 2022

View Certificate

Professional Memberships

Nepal Engineering Council

Professional Engineering Body

October 2024 - Present

Active member of Nepal's premier engineering professional body, committed to maintaining high standards of engineering practice and professional development.

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!

Location

Tokha-7, Kathmandu, Nepal

Email

Social

Available for opportunities

Send a Message

I'll get back to you as soon as possible.