Portrait
Fatema Tuj Johora Faria
AI Engineer II
Astha.IT
About Me

Hi! I am Fatema Tuj Johora Faria, currently working as an AI Engineer II at Astha.IT. I design, develop, and deploy generative AI applications with a strong focus on Large Language Models, Large Multimodal Models, and Retrieval-Augmented Generation (RAG). My work spans building LLM-based agents, multimodal AI agents, and multi-agent architectures that automate complex tasks and enable data-driven insights. In my current role, I leverage cloud infrastructure such as AWS S3, EC2, ECR, and App Runner to build scalable, efficient, and reliable AI systems, while also focusing on user-friendly interfaces that make AI interactions intuitive.

Previously, as Senior Application Developer at Dexian (Bangladesh) Limited, I led the architecture of generative AI systems for production-grade deployment using Azure OpenAI, Azure SQL, Azure Blob Storage, and AlloyDB for high-performance vector search, oversaw proof-of-concept development to translate stakeholder requirements into feasible solutions, and mentored junior developers on coding standards and architectural best practices.

Research interests: Large Language Models, Large Multimodal Models, LLM & Multimodal AI Agents, Human–AI Interaction, NLP for Social Good, NLP for Low-Resource Languages, AI in Healthcare, Vision-Language Models, Trustworthy AI, and Computer Vision.

I am open to collaborative opportunities that align with my research goals. Feel free to reach out at fatema.faria142@gmail.com (personal) or ftj.faria@asthait.com (official).

Curriculum Vitae
Education
  • Ahsanullah University of Science and Technology
    Ahsanullah University of Science and Technology
    B.Sc. in Computer Science and Engineering
    CGPA 3.302/4.00 · Supervisor: Dr. Mohammad Shafiul Alam · Co-supervisor: Khan Md Hasib
    2019 - 2023
Experience
  • Astha.IT
    Astha.IT
    AI Engineer II
    Nov. 2025 - present
  • Dexian (Bangladesh) Limited
    Dexian (Bangladesh) Limited
    Senior Application Developer
    Jul. 2025 - Nov. 2025
  • Dexian (Bangladesh) Limited
    Dexian (Bangladesh) Limited
    Application Developer
    May 2024 - Jul. 2025
  • National Research Foundation of Korea / National Institute of Health, South Korea
    National Research Foundation of Korea / National Institute of Health, South Korea
    Remote Research Assistant
    Jun. 2024 - present
Honors & Awards
  • 11th IEEE i-COSTE 2025 Scholarship Award — research excellence & paper presentation of "PotatoGANs"
    Nov. 2025
  • Achievement Award, Excellence in Strategic Leadership & Agile Project Delivery — Dexian (Bangladesh) Limited
    Aug. 2025
  • DL Sprint 2.0 - BUET CSE Fest 2023 — Team AustPhoenix, 10th of 94
    2023
  • Top 5 Poster Presentation, Research Symposium 2023, AUST
    Jun. 2023
  • Codeware 19 - Intra AUST Programming Contest — commended for technical competence
    Oct. 2019
News (view all )
2026
Reached 200+ citations on my Google Scholar profile!
May 31
One of my research papers titled "PotatoGANs: Utilizing Generative Adversarial Networks, Instance Segmentation, and Explainable AI for Enhanced Potato Disease Identification and Classification" has been published in the 11th IEEE International Conference on Sustainable Technology and Engineering (IEEE i-COSTE 2025).
Mar 31
Reached 150+ citations on my Google Scholar profile!
Feb 28
2025
Participated in the Agile Transformation Workshop 2025 organized by Astha.IT, gaining hands-on experience with sprint planning, backlog grooming, user story mapping, daily stand-ups, sprint reviews, and retrospectives.
Dec 01
Awarded a 50% registration fee scholarship for research excellence and paper presentation of "PotatoGANs" at the 11th IEEE i-COSTE 2025.
Nov 02
Joined as AI Engineer II at Astha.IT!
Nov 01
Reached 100+ citations on my Google Scholar profile!
Oct 31
One of my research works titled "PotatoGANs: Utilizing Generative Adversarial Networks, Instance Segmentation, and Explainable AI for Enhanced Potato Disease Identification and Classification" has been accepted for presentation and publication at the 11th IEEE i-COSTE 2025 (IEEE).
Oct 02
One of my studies titled "Unraveling the Dominance of Large Language Models Over Transformer Models for Bangla Natural Language Inference: A Comprehensive Study" has been published in the 4th International Conference on Computing and Communication Networks (ICCCNet-2024) (Springer).
Oct 01
Selected Publications (view all )
PotatoGANs: Utilizing Generative Adversarial Networks, Instance Segmentation, and Explainable AI for Enhanced Potato Disease Identification and Classification

Fatema Tuj Johora Faria*, Mukaffi Bin Moin*, Mohammad Shafiul Alam*, Ahmed Al Wase, Md. Rabius Sani, Khan Md Hasib (* equal contribution)

11th IEEE International Conference on Sustainable Technology and Engineering (IEEE i-COSTE 2025) 2025

Proposes PotatoGANs, using CycleGAN/Pix2Pix to synthesize realistic diseased-potato images for data augmentation, combined with three Explainable AI methods (Grad-CAM, Grad-CAM++, Score-CAM) across three CNN backbones for interpretable disease classification.

PotatoGANs: Utilizing Generative Adversarial Networks, Instance Segmentation, and Explainable AI for Enhanced Potato Disease Identification and Classification

Fatema Tuj Johora Faria*, Mukaffi Bin Moin*, Mohammad Shafiul Alam*, Ahmed Al Wase, Md. Rabius Sani, Khan Md Hasib (* equal contribution)

11th IEEE International Conference on Sustainable Technology and Engineering (IEEE i-COSTE 2025) 2025

Proposes PotatoGANs, using CycleGAN/Pix2Pix to synthesize realistic diseased-potato images for data augmentation, combined with three Explainable AI methods (Grad-CAM, Grad-CAM++, Score-CAM) across three CNN backbones for interpretable disease classification.

Towards Robust Chain-of-Thought Prompting with Self-Consistency for Remote Sensing VQA: An Empirical Study Across Large Multimodal Models

Fatema Tuj Johora Faria, Laith H. Baniata, Ahyoung Choi, Sangwoo Kang

Mathematics (MDPI), Vol. 13, Issue 18, Article 3046 2025

Evaluates GPT-4o, Grok 3, Gemini 2.5 Pro, and Claude 3.7 Sonnet on remote-sensing VQA using zero-shot, chain-of-thought, and self-consistency prompting (Self-GeoSense), reaching up to 94.69% accuracy on basic judging tasks with Grok 3.

Towards Robust Chain-of-Thought Prompting with Self-Consistency for Remote Sensing VQA: An Empirical Study Across Large Multimodal Models

Fatema Tuj Johora Faria, Laith H. Baniata, Ahyoung Choi, Sangwoo Kang

Mathematics (MDPI), Vol. 13, Issue 18, Article 3046 2025

Evaluates GPT-4o, Grok 3, Gemini 2.5 Pro, and Claude 3.7 Sonnet on remote-sensing VQA using zero-shot, chain-of-thought, and self-consistency prompting (Self-GeoSense), reaching up to 94.69% accuracy on basic judging tasks with Grok 3.

BanglaCalamityMMD: A Comprehensive Benchmark Dataset for Multimodal Disaster Identification in the Low-Resource Bangla Language

Fatema Tuj Johora Faria, Mukaffi Bin Moin, Busra Kamal Rafa, Swarnajit Saha, Md. Mahfuzur Rahman, Khan Md Hasib, M. F. Mridha

International Journal of Disaster Risk Reduction, Vol. 130, Article 105800 2025

Introduces BanglaCalamityMMD, a 7,903-sample multimodal (text+image) benchmark across seven disaster categories, and DisasterMultiFusionNet, which fuses Swin Transformer and mBERT to reach 85.25% accuracy, a 5.35% gain over the best unimodal baseline.

BanglaCalamityMMD: A Comprehensive Benchmark Dataset for Multimodal Disaster Identification in the Low-Resource Bangla Language

Fatema Tuj Johora Faria, Mukaffi Bin Moin, Busra Kamal Rafa, Swarnajit Saha, Md. Mahfuzur Rahman, Khan Md Hasib, M. F. Mridha

International Journal of Disaster Risk Reduction, Vol. 130, Article 105800 2025

Introduces BanglaCalamityMMD, a 7,903-sample multimodal (text+image) benchmark across seven disaster categories, and DisasterMultiFusionNet, which fuses Swin Transformer and mBERT to reach 85.25% accuracy, a 5.35% gain over the best unimodal baseline.

Analyzing Diagnostic Reasoning of Vision–Language Models via Zero-Shot Chain-of-Thought Prompting in Medical Visual Question Answering

Fatema Tuj Johora Faria, Laith H. Baniata, Ahyoung Choi, Sangwoo Kang

Mathematics (MDPI), Vol. 13, Issue 14, Article 2322 2025

Proposes a zero-shot chain-of-thought prompting framework that makes vision-language model reasoning explicit for medical VQA; on PMC-VQA, Gemini 2.5 Pro reaches 72.48% accuracy, ahead of Claude 3.5 Sonnet and GPT-4o Mini.

Analyzing Diagnostic Reasoning of Vision–Language Models via Zero-Shot Chain-of-Thought Prompting in Medical Visual Question Answering

Fatema Tuj Johora Faria, Laith H. Baniata, Ahyoung Choi, Sangwoo Kang

Mathematics (MDPI), Vol. 13, Issue 14, Article 2322 2025

Proposes a zero-shot chain-of-thought prompting framework that makes vision-language model reasoning explicit for medical VQA; on PMC-VQA, Gemini 2.5 Pro reaches 72.48% accuracy, ahead of Claude 3.5 Sonnet and GPT-4o Mini.

MultiBanFakeDetect: Integrating Advanced Fusion Techniques for Multimodal Detection of Bangla Fake News in Under-Resourced Contexts

Fatema Tuj Johora Faria, Mukaffi Bin Moin, Zayeed Hasan, Md. Arafat Alam Khandaker, Niful Islam, Khan Md Hasib, M. F. Mridha

International Journal of Information Management Data Insights, Vol. 5, Issue 2, Article 100347 2025

Introduces the MultiBanFakeDetect dataset and MultiFusionFake, an early-fusion text+image model (DenseNet-169 + mBERT) for Bangla fake news detection, reaching 79.69% accuracy versus 73.13% for a text-only baseline.

MultiBanFakeDetect: Integrating Advanced Fusion Techniques for Multimodal Detection of Bangla Fake News in Under-Resourced Contexts

Fatema Tuj Johora Faria, Mukaffi Bin Moin, Zayeed Hasan, Md. Arafat Alam Khandaker, Niful Islam, Khan Md Hasib, M. F. Mridha

International Journal of Information Management Data Insights, Vol. 5, Issue 2, Article 100347 2025

Introduces the MultiBanFakeDetect dataset and MultiFusionFake, an early-fusion text+image model (DenseNet-169 + mBERT) for Bangla fake news detection, reaching 79.69% accuracy versus 73.13% for a text-only baseline.

SentimentFormer: A Transformer-Based Multimodal Fusion Framework for Enhanced Sentiment Analysis of Memes in Under-Resourced Bangla Language

Fatema Tuj Johora Faria, Laith H. Baniata, Mohammad H. Baniata, Mohannad A. Khair, Ahmed Ibrahim Bani Ata, Chayut Bunterngchit, Sangwoo Kang

Electronics (MDPI), Vol. 14, Issue 4, Article 799 2025

Presents SentimentFormer, an intermediate-fusion transformer combining SwiftFormer and mBERT for Bangla meme sentiment analysis on the MemoSen dataset, reaching 79.04% accuracy versus 73.31% (text-only) and 64.72% (image-only).

SentimentFormer: A Transformer-Based Multimodal Fusion Framework for Enhanced Sentiment Analysis of Memes in Under-Resourced Bangla Language

Fatema Tuj Johora Faria, Laith H. Baniata, Mohammad H. Baniata, Mohannad A. Khair, Ahmed Ibrahim Bani Ata, Chayut Bunterngchit, Sangwoo Kang

Electronics (MDPI), Vol. 14, Issue 4, Article 799 2025

Presents SentimentFormer, an intermediate-fusion transformer combining SwiftFormer and mBERT for Bangla meme sentiment analysis on the MemoSen dataset, reaching 79.04% accuracy versus 73.31% (text-only) and 64.72% (image-only).

All publications