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 like turning messy, ambiguous business problems into reliable AI systems that people trust in production. Over the last 2.5 years, I've gained hands-on expertise in Multi-Agent Systems, AI Agent Orchestration, Retrieval-Augmented Generation (RAG) Pipelines, and LLMOps Infrastructure to build and deploy scalable, production-grade AI.

Research Interests
Large Language Models Vision-Language Models AI Agents Trustworthy AI AI Security AI Safety
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). For a detailed overview of my experience and qualifications: Curriculum Vitae
Education (view details )
Work Experience (view details )
Astha.IT
Astha.IT
Nov. 2025 - Present
AI Engineer II
Dexian (Bangladesh) Limited
Dexian (Bangladesh) Limited
Jul. 2025 - Oct. 2025
Senior Application Developer
Dexian (Bangladesh) Limited
Dexian (Bangladesh) Limited
May 2024 - Jun. 2025
Application Developer
News 2026 (view details )
Selected Publications All Publications
CLAIR-Fin: An Adversarial Multi-Agent Framework for Claim-Level Verification and Adaptive Debate in Cross-Modal Financial QA
Published
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

FinNLP-2026 @ EMNLP-2026

arXiv PDF Code Dataset

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

FinNLP-2026 @ EMNLP-2026

arXiv PDF Code Dataset

ChannelGuard: From Borrowed Safety to Application-Controlled Defenses in Multi-Agent LLMs
Under Review
ChannelGuard: From Borrowed Safety to Application-Controlled Defenses in Multi-Agent LLMs

Elias Hossain, Md Mehedi Hasan Nipu, Fatema Tuj Johora Faria, Shubhashis Roy Dipta, Maleeha Sheikh, Tasfia Nuzhat Ornee, Niloofar Yousefi

arXiv

ChannelGuard: From Borrowed Safety to Application-Controlled Defenses in Multi-Agent LLMs
Under Review
ChannelGuard: From Borrowed Safety to Application-Controlled Defenses in Multi-Agent LLMs

Elias Hossain, Md Mehedi Hasan Nipu, Fatema Tuj Johora Faria, Shubhashis Roy Dipta, Maleeha Sheikh, Tasfia Nuzhat Ornee, Niloofar Yousefi

arXiv

LabourCrew: A Multi-Agent RAG Framework for Trustworthy Adversarial Deliberation and Statutory Reasoning over Labour Law
LabourCrew: A Multi-Agent RAG Framework for Trustworthy Adversarial Deliberation and Statutory Reasoning over Labour Law

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

arXiv Code Dataset

LabourCrew: A Multi-Agent RAG Framework for Trustworthy Adversarial Deliberation and Statutory Reasoning over Labour Law
LabourCrew: A Multi-Agent RAG Framework for Trustworthy Adversarial Deliberation and Statutory Reasoning over Labour Law

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

arXiv Code Dataset

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

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

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

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

Technical Skills
Programming Languages Python (Pandas, NumPy, SciPy, Seaborn), Java, C++, JavaScript, TypeScript
Deep Learning Frameworks TensorFlow, Keras, PyTorch
LLM Application Frameworks LangChain, LangGraph, LlamaIndex, CrewAI, OpenAI Agent SDK, Claude Agent SDK
LLM Evaluation and Observability LangSmith, Langfuse, RAGAS, DeepEval
Vector Databases Milvus, ChromaDB, Qdrant, PostgreSQL (pgvector)
Cloud Services (Azure) Azure AI Foundry, Azure SQL Database, Azure Blob Storage, Azure App Service
Cloud Services (AWS) Amazon ECR, Amazon EC2, Amazon S3, Amazon SES
Cloud Services (GCP) Google Cloud Storage, Google Cloud Run, Google Cloud SQL
Others Hugging Face, LLM Fine-tuning, OpenCV, PostgreSQL, React, Docker, Microsoft Bot Framework, WebSocket, Redis