Skip to content
View ahmedshahriar's full-sized avatar
🏠
Working from home
🏠
Working from home
280 followers · 488 following

Achievements

Achievement: YOLOAchievement: Pair ExtraordinaireAchievement: QuickdrawAchievement: StarstruckAchievement: Arctic Code Vault ContributorAchievement: Pull Sharkx3

Achievements

Achievement: YOLOAchievement: Pair ExtraordinaireAchievement: QuickdrawAchievement: StarstruckAchievement: Arctic Code Vault ContributorAchievement: Pull Sharkx3

Highlights

  • Pro

Block or report ahmedshahriar

Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
ahmedshahriar/README.md

Hello there

Ahmed Shahriar Sakib's LinkedIn ahmed__shahriar | Twitter Ahmed Shahriar Sakib's Kaggle Profile

ahmedshahriar


I am Ahmed Shahriar Sakib. With a background as a Software Engineer, I specialize in data analytics, machine learning, natural language processing (NLP), web crawling, and automation.

I recently completed my MASc in Management Science and Engineering at the University of Waterloo, where my research focused on machine learning and NLP, including work with large language models. I hold a BSc in Software Engineering (2019) and have since been building scalable software systems and applying data-driven technologies to solve real-world problems. To complement my technical experience, I’ve earned professional certifications from AWS, Microsoft, IBM, and DeepLearning.AI, covering cloud computing, AI/ML, and data science.

🔵 List of my featured Projects - ahmedshahriar.com/portfolio
🔵 Kaggle notebooks - kaggle.com/ahmedshahriarsakib/code
🔵 Kaggle datasets - kaggle.com/ahmedshahriarsakib/datasets

Pinned Loading

  1. restaurant-menu-pricing restaurant-menu-pricing Public

    Predict menu prices from 5M+ UberEats menus with an end-to-end MLOps pipeline: crawl → DWH → curate → train → deploy on Azure ML (MLflow) via APIM & CLIs.

    Python 3

  2. llm-ghostwriter llm-ghostwriter Public

    MLOps-driven LLM RAG assistant that learns your writing style from your online content, with an FTI pipeline (Features → Training → Inference) , RAG for context grounding, and ZenML orchestration.

    Python

  3. TwitterCelebrityMatcher TwitterCelebrityMatcher Public

    Match celebrity users with their respective tweets by making use of Semantic Textual Similarity on over 900+ celebrity users' 2.5 million+ crawled tweets utilizing SBERT, streamlit, tweepy and FastAPI

    Python 13 2

  4. PulsePoint-Data-Analytics PulsePoint-Data-Analytics Public

    EDA, data processing, cleaning and extensive geospatial analysis on a selenium based web crawled dataset

    HTML 6 2

  5. bd-medicine-scraper bd-medicine-scraper Public

    Scrapy-Django PostgreSQL integrated API with Proxy IP configuration that scrapes all medicine data (meds, prices, generics, companies, indications) from Bangladesh (30k+ pages)

    Python 71 29

  6. youtube-comment-scraper youtube-comment-scraper Public

    This script will dump youtube video comments to a CSV from youtube video links. Video links can be placed inside a variable or list or CSV

    Jupyter Notebook 47 16