Amaan Poonawala
Welcome to My Portfolio

Hi, I'm Amaan Poonawala

AI Developer | Data Science

View My WorkDownload ResumeGet in Touch

About Me

Your Name - Profile Picture

A Bit About My Journey

Over the past two years, I’ve built a strong foundation in software development, data science, and AI through a structured, hands-on, project-driven approach.

Full-Stack Development: Started with HTML, CSS, JavaScript, React, Node.js, and MongoDB to understand real-world system design and deployment.

Programming Core: Deepened JavaScript (closures, async, OOP) and transitioned to Python with a focus on core concepts and data structures.

Data Science: Gained experience in web scraping (Selenium, Scrapy), data analysis (Pandas, NumPy, Seaborn), and SQL through projects like a YouTube analytics tool and IMDb explorer.

Machine Learning: Built models for fraud detection and audiobook prediction using regression, clustering, decision trees, and neural networks (TensorFlow, PyTorch).

Advanced AI & NLP: Explored Transformers and LLMs. Fine-tuned a sentiment model on 1M+ YouTube comments and integrated it into a recommendation system.

AI Product Development: Recently used LangChain and LlamaIndex to build full-stack AI apps like an IELTS essay evaluator, combining RAG pipelines, prompt engineering, and deep learning.

My Skillset

AI Frameworks & Libraries
LangChainLangGraphCrewAITransformersOpenCVMediaPipe
Machine Learning & Data Science
PythonTensorFlowPyTorchSeabornScikit-learnPandasNumPyMatplotlib
Full-Stack Development
JavaScriptTypeScriptReact.jsNext.jsHTMLCSSTailwind CSSFastAPIFlaskDjango
Databases & Vector DBs
PostgreSQLMySQLMongoDBRedisPineconeFAISS
Web Scraping & Automation
BeautifulSoupSeleniumScrapyplaywright
DevOps & Tools
GitDockerGitHub ActionsAWSVPS HostingJenkins

Featured Projects

YouTube AI Analyzer
YouTube AI Analyzer
YouTube AI Analyzer is a full-stack application that evaluates YouTube videos and comments using AI. It offers summaries, sentiment analysis, and interactive visualizations for efficient video comparison and feedback extraction.

Tech Stack:

LangChain
FastAPI
LLM
FAISS
PostgreSQL
...
Portfolio AI Assistant
Portfolio AI Assistant
Portfolio AI Assistant is an agentic Retrieval-Augmented Generation (RAG) chatbot embedded in my portfolio. It provides precise answers about my projects, skills, certifications, and learning journey, handling multi-turn conversations with context-aware retrieval and hybrid search.

Tech Stack:

FastAPI
LangChain
Pinecone
FlashRank
Custom Hybrid Retriever
...
Fine-tune XLM-RoBERTa
Fine-tune XLM-RoBERTa
A fine-tuned multilingual XLM-RoBERTa model optimized for YouTube comment sentiment analysis. Trained on over 1 million labeled comments, it significantly improves accuracy in detecting positive, neutral, and negative sentiments compared to the Twitter-trained baseline.

Tech Stack:

Transformers (Hugging Face)
XLM-RoBERTa
Datasets
AutoTokenizer
AutoModelForSequenceClassification
...
YouTube Comment Sentiment Curation
YouTube Comment Sentiment Curation
Curated a large-scale dataset of 1M+ YouTube comments annotated with sentiment labels (Positive, Neutral, Negative) across multiple domains and countries, enriched with metadata for NLP, sentiment analysis, and LLM fine-tuning.

Tech Stack:

YouTube Data API v3
Google Gemini (Generative AI)
Aiohttp
Asyncio
Pandas
...
Multi-Tenant Chat Application
Multi-Tenant Chat Application
A real-time multi-tenant chat system with strict tenant isolation, role-based access control, and secure authentication. Designed for organizations that need private communication environments with Super Admin oversight and Admin-managed tenants.

Tech Stack:

FastAPI
JWT (Cookie-based Authentication)
PostgreSQL
MongoDB
Redis (Pub/Sub, Caching)
...

Get In Touch

Send me a message
I'd love to hear from you! You can also connect with me on the platforms below.