Draft:Muhammad Yasir
Submission declined on 24 May 2026 by Andrew Gray (talk).
Where to get help
How to improve a draft
You can also browse Wikipedia:Featured articles and Wikipedia:Good articles to find examples of Wikipedia's best writing on topics similar to your proposed article. Improving your odds of a speedy review To improve your odds of a faster review, tag your draft with relevant WikiProject tags using the button below. This will let reviewers know a new draft has been submitted in their area of interest. For instance, if you wrote about a female astronomer, you would want to add the Biography, Astronomy, and Women scientists tags. Editor resources
|  |
Comment: The only sources given here are his own LinkedIn and Github pages; we would need to see multiple independent sources with significant coverage for this to be suitable for an article. Andrew Gray (talk) 18:08, 24 May 2026 (UTC)
 | The topic of this draft may not meet Wikipedia's general notability guideline. (May 2026) |
Muhammad Yasir | |
|---|---|
محمد یاسر | |
 Muhammad Yasir, 2025 | |
| Born | Pakistan |
| Other name | devxyasir |
| Education | BS Information Technology |
| Alma mater | Bahauddin Zakariya University |
| Occupations |
|
| Years active | 2021–present |
| Known for | AI automation systems, RAG systems, OCR and NLP applications |
| Website | github |
Muhammad Yasir (online handle: devxyasir) is a Pakistani software developer and artificial intelligence engineer currently based in Dubai, United Arab Emirates. He holds a Bachelor of Science in Information Technology from Bahauddin Zakariya University (BZU), Lodhran Campus, and has worked on projects in machine learning, natural language processing (NLP), computer vision, and full-stack software development.[citation needed] He has been active in independent software development since approximately 2021. [citation needed]
Early life and education
[edit]Muhammad Yasir was born and raised in Pakistan.[citation needed] He enrolled at Bahauddin Zakariya University, Lodhran Campus, in the Information Technology program, graduating in 2025 with a GPA of 3.14.[citation needed] During his studies he undertook coursework and practical work in programming, systems design, database management, and applied artificial intelligence. [citation needed] His academic background formed the foundation for his subsequent professional work in AI engineering and software development. [citation needed]
Career
[edit]Internships and early professional work
[edit]While completing his undergraduate degree, Yasir worked as a Python Developer intern at BZU Lodhran, where he was involved in programming and scripting tasks within the institution.[citation needed] He subsequently completed an internship as an AI Engineer at Codiux, a software company, during which he contributed to artificial intelligence development projects. [citation needed] These positions provided him with professional experience in applied Python development and AI engineering prior to graduation. [citation needed]
Relocation to Dubai
[edit]Following the completion of his degree, Yasir relocated to Dubai, UAE, where he has continued working in software and AI development.[citation needed] He has been engaged in the UAE technology sector, pursuing roles in artificial intelligence and data engineering.[citation needed]
Projects and work
[edit]Yasir has developed a range of publicly documented software projects, primarily hosted on GitHub under the handle devxyasir.[1] His work spans AI automation, document intelligence, and developer tooling.
TrOCR-based document extraction
[edit]One of his documented projects involves a document extraction pipeline built on Microsoft TrOCR, a transformer-based optical character recognition (OCR) model.[citation needed] The system was designed to process document images and extract structured text using NLP-based post-processing components.[citation needed]
AI agents and email automation
[edit]Yasir developed AI agent systems for task automation, including pipelines for email processing and multi-step workflow orchestration. [citation needed] These systems use large language model APIs in combination with scripted backend components. [citation needed]
Retrieval-Augmented Generation systems
[edit]He has built retrieval-augmented generation (RAG) applications that combine document retrieval mechanisms with generative language models to produce outputs grounded in source documents.[citation needed] RAG systems of this type are widely used in knowledge management and document question-answering contexts.[citation needed]
Predictive analytics and computer vision
[edit]Yasir's portfolio includes supervised machine learning-based predictive analytics systems and computer vision applications, among them a number plate detection project.[citation needed] These projects were implemented using Python-based frameworks including TensorFlow, PyTorch, and OpenCV. [citation needed]
Competitors-Analysis-Agents
[edit]A public repository on his GitHub account, titled Competitors-Analysis-Agents, implements a multi-agent system for automated competitive intelligence gathering.[citation needed] The system uses the Brave Search API for web data retrieval and the Prefect framework for workflow orchestration. [citation needed] Its stated purpose is the automated collection and summarization of competitor information from publicly available web sources.[citation needed]
BeamLab
[edit]Yasir developed a project called BeamLab, described as a command-line AI coding agent built in Python. [citation needed] The tool was designed to assist developers with code generation and editing tasks via a terminal interface, drawing on multiple open-source large language models including Qwen 2.5 Coder, DeepSeek R1, and Llama 3.1. [citation needed] The project included a persistent session system using SQLite, a sliding window memory mechanism with LLM-based compression, and a context-aware model routing system. [citation needed]
Recode
[edit]A separate project referred to as Recode is described as a Visual Studio Code-based AI coding editor intended as an alternative to tools such as Cursor and Windsurf in the AI-assisted development tooling space.[citation needed] Development work on Recode included brand identity design and a custom design system. [citation needed]
Technical skills and methods
[edit]Yasir's documented work reflects competencies in the following technical areas:[citation needed]
- Languages and frameworks: Python,
FastAPI, Flask, JavaScript
- AI and ML: Machine learning, deep learning,
natural language processing, computer vision, OCR
- LLM tooling: Retrieval-augmented generation,
AI agent frameworks, prompt engineering, model fine-tuning via LoRA and QLoRA methods
- Infrastructure and automation: Prefect workflow orchestration,
SQLite, self-hosted open-source deployments, Docker, browser automation
- Full-stack development: Web frontend interfaces,
REST API design, Chrome extension development
He has consistently employed open-source and self-hosted tooling across his projects.[citation needed]
Public presence
[edit]Yasir maintains a public GitHub profile under the username devxyasir, where a number of his software projects are available as open-source repositories.[2] He also maintains a LinkedIn profile under the same handle, documenting his professional background and project history.[3]
See also
[edit]References
[edit]- ↑ "devxyasir — GitHub profile". GitHub. Retrieved 2026-05-23.
- ↑ "devxyasir — GitHub profile". GitHub. Retrieved 2026-05-23.
- ↑ "Muhammad Yasir — LinkedIn". LinkedIn. Retrieved 2026-05-23.
- provide significant coverage: discuss the person in detail, not brief mentions or interviews lacking independent analysis;
- are reliable: from reputable outlets with editorial oversight;
- are independent: not connected to the person, such as interviews, press releases, the subject's own website, or sponsored content.
Please add references that meet all three of these criteria. If none exist, the subject is not yet suitable for Wikipedia.