Hi!!! This is Fatema Tuj Johora Faria, currently working as a Senior Application Developer at Dexian (Bangladesh) Limited. My expertise lies in designing, developing, and deploying generative AI-based applications with a strong focus on Large Language Models (LLMs), Large Multimodal Models (LMMs), Retrieval-Augmented Generation (RAG), as well as LLM agents and their multi-agent architectures for automating complex tasks and supporting data-driven insights. I also specialize in designing user-friendly interfaces that simplify AI interactions and provide an intuitive experience for users.

In my role, I focus on delivering high-impact work through the following key areas:

(1) Proof of Concepts (PoCs): I oversee the development of PoCs to explore forward-thinking ideas by analyzing client and stakeholder requirements and translating them into business goals. I rapidly prototype solutions and iterate based on feedback to assess feasibility, reduce risks, and enable informed decision-making for full-scale implementation, while ensuring alignment with the long-term product vision.
(2) Leadership in Project Execution: I lead the architecture of generative AI systems for production-grade deployment, utilizing Azure OpenAI for LLM integration, Azure SQL for robust data management, Azure Blob Storage for scalable asset handling, and AlloyDB for high-performance vector search. I design modular, domain-specific AI pipelines optimized for low-latency inference and deploy them efficiently via Azure Web App, focusing on reducing operational overhead and ensuring cost-effective, real-world performance.
(3) Mentorship: I mentor Junior Application Developers by guiding them on coding standards, architectural best practices, and professional growth, helping them contribute effectively to our projects.

My Primary Research Interests Include:

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

I am open to collaborative opportunities that align with my research goals and passions. If you have any inquiries or wish to discuss potential collaborations, please feel free to reach out. You can contact me via email at Personal: fatema.faria142@gmail.com or Official: fatema.faria@dexian.com.

⚡ Recent Highlights

September 2025
Our paper, "BanglaCalamityMMD: A Comprehensive Benchmark Dataset for Multimodal Disaster Identification in the Low-Resource Bangla Language", has been accepted for publication in the International Journal of Disaster Risk Reduction.
July 2025
Promoted to Senior Application Developer at Dexian (Bangladesh) Limited.
July 2025
Our research work titled "Analyzing Diagnostic Reasoning of Vision–Language Models via Zero-Shot Chain-of-Thought Prompting in Medical Visual Question Answering" has been published in Mathematics (MDPI), Vol. 13, Issue 14, Article 2322.
June 2025
One of our research works, "MultiBanFakeDetect: Integrating Advanced Fusion Techniques for Multimodal Detection of Bangla Fake News in Under-Resourced Contexts", has been published in the International Journal of Information Management Data Insights, Vol. 5, Issue 2.
June 2025
Our conference paper, "Uddessho: An Extensive Benchmark Dataset for Multimodal Author Intent Classification in Low-Resource Bangla Language", has been published in the ICITA 2024 Proceedings.
February 2025
One of our studies, "SentimentFormer: A Transformer-Based Multimodal Fusion Framework for Enhanced Sentiment Analysis of Memes in Under-Resourced Bangla Language", has been published in Electronics (MDPI), Vol. 14(4), 799.
November 2024
One of our papers, "Investigating the Predominance of Large Language Models in Low-Resource Bangla Language over Transformer Models for Hate Speech Detection: A Comparative Analysis", has been published in Mathematics (MDPI), Vol 12, Issue 23.
October 2024
Attended ICITA 2024, Sydney, Australia.
October 2024
Attended ICCCNet 2024, Manchester, UK.
September 2024
Attended IEEE TENSYMP 2024, New Delhi.
August 2024
Our research article, "Uddessho: An Extensive Benchmark Dataset for Multimodal Author Intent Classification in Low-Resource Bangla Language", has been accepted for presentation at the 18th International Conference on Information Technology and Applications (ICITA 2024).
June 2024
One of our research works, "Motamot: A Dataset for Revealing the Supremacy of Large Language Models over Transformer Models in Bengali Political Sentiment Analysis", has been accepted at the The IEEE Region 10 Symposium (TENSYMP 2024).
June 2024
Started working as a Remote Research Assistant under the funded projects by the National Research Foundation of Korea and the National Institute of Health, South Korea.
May 2024
Two of our papers, "Unraveling the Dominance of Large Language Models Over Transformer Models for Bangla Natural Language Inference: A Comprehensive Study" and "Exploring Explainable AI Techniques for Improved Interpretability in Lung and Colon Cancer Classification", have been accepted at the 4th International Conference on Computing and Communication Networks (ICCCNet-2024).
May 2024
Joined as Application Developer at Dexian (Bangladesh) Limited.
Visitor Map