AI Engineer II · AI Agents · Multimodal AI · AI Safety · AI Security ·Trustworthy AI
I am Fatema Tuj Johora Faria, currently working as an AI Engineer II at Astha.IT. I build Agentic AI applications for internal automation and client-facing use cases, with a focus on LLM Agents, Retrieval-Augmented Generation (RAG), and Model Context Protocol (MCP). My work spans the full AI application lifecycle, from solution design and development to deployment.
Previously, I worked as a Senior Application Developer at Dexian (Bangladesh) Limited, where I developed Generative AI solutions based on client and stakeholder requirements. I collaborated with cross-functional teams to translate business requirements into scalable software solutions and contributed through code reviews, technical guidance, and knowledge-sharing with junior developers.
I have hands-on experience with AWS, Google Cloud Platform (GCP), and Microsoft Azure for AI application deployment, cloud infrastructure, and production environments.
I earned my Bachelor's degree in Computer Science and Engineering from Ahsanullah University of Science and Technology.
I am interested in developing AI systems that can reason reliably, operate autonomously, and remain safe and dependable in real-world environments.
- 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.
- AI Safety: Developing AI systems that remain safe, robust, and controllable under uncertainty, unexpected inputs, and real-world conditions.
- AI Security: Defending language models and AI agents against adversarial attacks, prompt injection, and malicious inputs.
- Trustworthy AI: Advancing AI systems that promote fairness, explainability, and reliability across diverse environments.
- AI for Databases: Developing AI systems that translate natural language into SQL, reason over database schemas, and enable more intuitive access to structured data across diverse use cases.
- AI for Social Good: Building accessible and scalable AI solutions that address real-world societal challenges and deliver meaningful impact.
| Programming | Python · Java · C++ |
| AI / ML | PyTorch · TensorFlow · Keras · OpenCV · NumPy · SciPy · Pandas |
| LLM & Agents | LangChain · LangGraph · LlamaIndex · LlamaAgents · RAG · MCP |
| LLM Evaluation | LangSmith · Langfuse · Ragas · DeepEval |
| Web & APIs | FastAPI · React · JavaScript · TypeScript · Tailwind CSS · WebSocket |
| Databases | PostgreSQL · MySQL · MongoDB · AlloyDB · pgvector |
| Vector Databases | AlloyDB (pgvector) · ChromaDB · Milvus |
| Microsoft Azure | Azure OpenAI · Azure SQL · Azure App Service · Azure Blob Storage · Azure Functions · Azure Boards |
| AWS | ECR · App Runner · EC2 · S3 |
| Google Cloud | Google Cloud Storage · App Engine · Compute Engine |
| Tools & Platforms | Docker · Apache Airflow · Jira · Microsoft Bot Services |
"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
Open to research collaborations, technical discussions, and interesting ideas in AI.