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

Greetings! I am Fatema Tuj Johora Faria, and I earned a Bachelor of Science in Computer Science and Engineering from Ahsanullah University of Science and Technology, Dhaka, Bangladesh.

I am currently working as an AI Engineer II at Astha.IT, where I bring around 2.5 years of full stack experience in AI applications. My work focuses on architecting, developing, and deploying production-grade agentic solutions. I have hands-on experience with Microsoft Azure, Amazon Web Services (AWS), and Google Cloud Platform (GCP) for building scalable, robust, and high-performance systems, while also focusing on user-friendly interfaces that make AI interactions intuitive.

I am always happy to collaborate, exchange ideas, and learn about new research directions. Please feel free to reach out to me at fatema.faria142@gmail.com (personal) or ftj.faria@asthait.com (official).
Research Interests

AI Reasoning & Autonomy:

  • LLM Reasoning: Exploring how large language models can achieve reliable, structured, and multi-step reasoning for tackling challenging real-world scenarios.
  • AI Agents: Examining how AI agents can plan, use tools, collaborate, and adapt to orchestrate complex tasks in dynamic environments.
  • Multimodal AI: Investigating how multimodal models can integrate and reason across diverse modalities (text + images) to improve contextual understanding and decision-making.

Safety, Security, & Alignment:

  • Trustworthy AI: Investigating how AI systems can achieve fairness, explainability, reliability, and accountability across real-world settings.
  • AI Security: Analyzing how language models can withstand adversarial attacks, prompt injection, malicious inputs, and other threats to their reliability and integrity.

Domain-Specific AI Applications:

  • AI for Databases: Investigating how AI can translate user natural language into SQL queries, reason over database schemas, and improve access to structured data across different use cases.
  • AI for Social Good: Exploring how AI can be designed and applied to address societal challenges through accessible, scalable, and impactful solutions.
Curriculum Vitae
Education (view details )
  • Ahsanullah University of Science and Technology
    Ahsanullah University of Science and Technology
    2019 - 2023
    Bachelor of Science in Computer Science and Engineering
  • National Ideal College
    National Ideal College
    2015 - 2017
    Higher Secondary Certificate
  • Motijheel Model School and College
    Motijheel Model School and College
    2009 - 2015
    Secondary School Certificate
Technical Skills
Programming Languages Python (NumPy, SciPy, Matplotlib, Pandas, Seaborn), Java, C++
Web Development JavaScript, TypeScript, Tailwind CSS, FastAPI, React
Databases MySQL, PostgreSQL, MongoDB
Deep Learning Frameworks TensorFlow, Keras, PyTorch
LLM Application Frameworks LangChain, LangGraph, LlamaIndex, LlamaAgents
Vector Databases AlloyDB for PostgreSQL (pgvector), ChromaDB, FAISS, Milvus
Cloud Services (Azure) Azure OpenAI, Azure SQL Database, Azure Container Registry, Azure App Service, Azure Blob Storage, Azure Boards, Azure Functions, Azure Bot Service
Cloud Services (AWS) Amazon ECR, AWS App Runner, Amazon EC2, Amazon S3, Amazon SES
Cloud Services (GCP) Google Cloud Storage, Google App Engine, Google Compute Engine
Others Docker, GitHub, OpenCV, Microsoft Bot Framework, WebSocket, Jira
News (view details )
2026
2025

Selected Publications

View all
CLAIR-Fin: An Adversarial Multi-Agent Framework for Claim-Level Verification and Adaptive Debate in Cross-Modal Financial QA
Selected Under Review
CLAIR-Fin: An Adversarial Multi-Agent Framework for Claim-Level Verification and Adaptive Debate in Cross-Modal Financial QA

Fatema Tuj Johora Faria, Mukaffi Bin Moin, Jubayer Al Mahmud, M. F. Mridha, Md. Alam Hossain

arXiv preprint

Selected Under Review
CLAIR-Fin: An Adversarial Multi-Agent Framework for Claim-Level Verification and Adaptive Debate in Cross-Modal Financial QA

Fatema Tuj Johora Faria, Mukaffi Bin Moin, Jubayer Al Mahmud, M. F. Mridha, Md. Alam Hossain

arXiv preprint

TeachMateGPT: A Multi-Agent Knowledge-Grounded Framework for Pedagogical Assessment Generation from Science Curriculum Materials
Selected Under Review
TeachMateGPT: A Multi-Agent Knowledge-Grounded Framework for Pedagogical Assessment Generation from Science Curriculum Materials

Fatema Tuj Johora Faria, Mukaffi Bin Moin, M. F. Mridha, Jubayer Al Mahmud

arXiv preprint

Selected Under Review
TeachMateGPT: A Multi-Agent Knowledge-Grounded Framework for Pedagogical Assessment Generation from Science Curriculum Materials

Fatema Tuj Johora Faria, Mukaffi Bin Moin, M. F. Mridha, Jubayer Al Mahmud

arXiv preprint

ChannelGuard: Safe Models Do Not Compose into Safe Multi-Agent Systems
Selected Under Review
ChannelGuard: Safe Models Do Not Compose into Safe Multi-Agent Systems

Elias Hossain, Md Mehedi Hasan Nipu, Fatema Tuj Johora Faria, Tasfia Nuzhat Ornee, Maleeha Sheikh

arXiv preprint

Selected Under Review
ChannelGuard: Safe Models Do Not Compose into Safe Multi-Agent Systems

Elias Hossain, Md Mehedi Hasan Nipu, Fatema Tuj Johora Faria, Tasfia Nuzhat Ornee, Maleeha Sheikh

arXiv preprint

Guiding Language Models to Be More Empathetic: Culturally Sensitive Mental Health Advice Generation Through Human-LLM Collaboration
Selected Under Review
Guiding Language Models to Be More Empathetic: Culturally Sensitive Mental Health Advice Generation Through Human-LLM Collaboration

Fatema Tuj Johora Faria, Mukaffi Bin Moin, Md. Mahfuzur Rahman, Khan Md Hasib, Jubayer Al Mahmud, M. F. Mridha

arXiv preprint

Selected Under Review
Guiding Language Models to Be More Empathetic: Culturally Sensitive Mental Health Advice Generation Through Human-LLM Collaboration

Fatema Tuj Johora Faria, Mukaffi Bin Moin, Md. Mahfuzur Rahman, Khan Md Hasib, Jubayer Al Mahmud, M. F. Mridha

arXiv preprint

All publications