Skip to content
View fatemafaria142's full-sized avatar
🏠
Working from home
🏠
Working from home
37 followers · 2 following

Block or report fatemafaria142

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

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

Report abuse
fatemafaria142/README.md

Hi there 🙋‍♀️

I am Fatema Tuj Johora Faria, currently working as an AI Engineer II at Astha.IT. In my professional role, I build LLM Agents and Multimodal AI Agents to automate complex workflows within internal company processes, using AWS cloud services for scalable and efficient deployment. I also guide interns on requirements analysis, code quality checks, and following best practices to deliver high-quality AI systems. I also specialize in designing user-friendly interfaces that simplify AI interactions and provide an intuitive experience for users.

Previously, I worked as a Senior Application Developer at Dexian (Bangladesh) Limited, where I developed proof-of-concept prototypes, architected intelligent AI pipelines, and contributed to production-ready AI solutions, gaining hands-on experience with Azure OpenAI, Azure SQL, Azure Blob Storage, AlloyDB for high-performance vector search, and scalable deployments via Azure Web App. I built modular, domain-specific AI pipelines optimized for low-latency inference and production-grade performance.

I earned my Bachelor's degree in Computer Science and Engineering from Ahsanullah University of Science and Technology, which laid the foundation for my passion for generative AI application development.

Primary Research Interests 🎯

I am primarily interested in the following areas, where I actively engage in research and development:

  • Large Language Models (LLMs)
  • Large Multimodal Models (LMMs)
  • LLM Agents
  • Multimodal AI Agents
  • Human–Computer Interaction
  • AI in Healthcare
  • NLP for Social Good
  • NLP for Low-Resource Languages
  • Vision-Language Models (VLMs)
  • Trustworthy AI
  • Computer Vision
Profile Views

Connect with me 🌐

Technical Skills 🧰

🔹 Programming Languages: Python (NumPy, SciPy, Matplotlib, Pandas, Seaborn), Java, C++
🔹 Web Development: JavaScript, TypeScript, Tailwind CSS, FastAPI, Flask, React, Streamlit
🔹 Database: MySQL, PostgreSQL, MongoDB
🔹 Deep Learning Frameworks: TensorFlow, Keras, PyTorch
🔹 LLM Application Frameworks: LangChain, LangGraph, LlamaIndex, LlamaAgents
🔹 LLM Evaluation Frameworks: LangSmith, Langfuse, Ragas, DeepEval
🔹 Vector Database: AlloyDB for PostgreSQL (pgvector extension), ChromaDB, FAISS
🔹 Cloud Services (Azure): Azure OpenAI, Azure SQL Database, Azure App Service, Azure Blob Storage, Azure Boards, Azure Functions, AlloyDB for PostgreSQL
🔹 Cloud Services (AWS): Elastic Container Registry (ECR), App Runner, Elastic Compute Cloud (EC2), S3 Buckets
🔹 Others: Prompt Engineering, Context Engineering, Docker, CrewAI, Jira Boards, GitHub, Github Copilot, Microsoft Bot Services, OpenCV, WebSocket, Apache Airflow, Hugging Face Transformers

Favorite Quote ✨

"The future of AI is not about creating machines that think like humans, but about building systems that learn from data and improve over time."
— Geoffrey Hinton

Github Stats 📊

GitHub Streak

Pinned Loading

  1. MultiBanFakeDetect-An-Extensive-Benchmark-Dataset-for-Multimodal-Bangla-Fake-News-Detection MultiBanFakeDetect-An-Extensive-Benchmark-Dataset-for-Multimodal-Bangla-Fake-News-Detection Public

    This study introduces MultiBanFakeDetect, a novel multimodal dataset for Bangla fake news detection, combining textual and visual information. It features TextFakeNet for text analysis and MultiFus…

    Jupyter Notebook 4 2

  2. SentimentFormer-A-Transformer-Based-Multi-Modal-Fusion-Framework-for-Sentiment-Analysis-of-Memes SentimentFormer-A-Transformer-Based-Multi-Modal-Fusion-Framework-for-Sentiment-Analysis-of-Memes Public

    This research developed a multimodal sentiment analysis framework for Bengali memes using the MemoSen dataset, leveraging both text and image data. It introduces SentimentFormer, which employs Ear…

    Jupyter Notebook 1 1

  3. BanglaCalamityMMD-A-Comprehensive-Benchmark-Dataset-for-Multimodal-Disaster-Identification BanglaCalamityMMD-A-Comprehensive-Benchmark-Dataset-for-Multimodal-Disaster-Identification Public

    Forked from Mukaffi28/BanglaCalamityMMD-A-Comprehensive-Benchmark-Dataset-for-Multimodal-Disaster-Identification

    This study presents a hybrid multimodal fusion technique for disaster identification in Bangla, combining text and image data using the "BanglaCalamityMMD" dataset. Employing DisasterTextNet, Disas…

    Jupyter Notebook

  4. Retinal-Fundus-Classification-using-XAI-and-Segmentation Retinal-Fundus-Classification-using-XAI-and-Segmentation Public

    This research enhances early disease diagnosis by analyzing retinal blood vessels in fundus images using deep learning. It employs eight pre-trained CNN models and Explainable AI techniques.

    Jupyter Notebook 11 4

  5. Large-Language-Models-Over-Transformer-Models-for-Bangla-NLI Large-Language-Models-Over-Transformer-Models-for-Bangla-NLI Public

    This research examines the performance of Large Language Models (GPT-3.5 Turbo and Gemini 1.5 Pro) in Bengali Natural Language Inference, comparing them with state-of-the-art models using the XNLI …

    Jupyter Notebook 3 1

  6. Vashantor-A-Large-scale-Multilingual-Benchmark-Dataset Vashantor-A-Large-scale-Multilingual-Benchmark-Dataset Public

    Forked from Mukaffi28/Vashantor-A-Large-scale-Multilingual-Benchmark-Dataset

    This study addresses the gap in translating Bangla regional dialects into standard Bangla by creating a large-scale multilingual benchmark dataset of 32,500 sentences in Bangla, Banglish, and Engli…

    Jupyter Notebook