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.
Work Experience
Software Engineer I, Machine Learning
Smart Data SolutionsNovember 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.
Machine Learning Engineer
Root Level AIJanuary 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.
Machine Learning Engineer
DoriITApril 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.
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
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.
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_indexessupport 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.
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.
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.
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.
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.
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.
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
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.
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
Core Languages
ML/DL Stack
Natural Language Processing
ML Infrastructure & MLOps
Data Systems
API & Deployment
Specializations
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
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.