I'm Md Raihanul Islam Bhuiyan, an AI Engineer with a Master's in Artificial Intelligence. I independently design, build, and deploy agentic AI systems, generative AI pipelines, and workflow automation tools.
I’m Md Raihanul Islam Bhuiyan, an AI Engineer with a Master’s in Artificial Intelligence. I independently design, build, and deploy agentic AI systems, generative AI pipelines, and workflow automation tools.
I am proficient in Python, LangChain, AutoGen, RAG, and cloud platforms (AWS, Azure), with a track record of delivering bespoke AI solutions for real-world business challenges with minimal supervision.
Built a multi-agent AI system for automated IT issue resolution integrating AutoGen and Azure AI services. Designed col-
laborating agents for issue classification, semantic retrieval from a vector knowledge base (historical tickets), and grounded
solution generation. Applied retrieval-grounded generation to ensure responses stayed within verified internal knowledge —
directly applicable to enterprise LLM deployment at scale.
Designed and deployed a production-grade full-stack agentic AI system generating structured course curricula from user-
defined inputs. Implemented a modular multi-agent pipeline (curriculum architect, validator, module-authoring agents) with
JSON schema validation loops to enforce output quality. Built a FastAPI backend with persistent storage and a React frontend;
deployed publicly for real-world use. Demonstrates end-to-end ownership of an LLM-powered product from design to live
deployment.
Independently designed and delivered bespoke AI solutions for document fraud detection — scoped requirements, selecting models, building pipelines, and deploying on AWS SageMaker with minimal supervision. Built multi-step agentic LLM workflows (GPT-4, LLaMA, AWS Bedrock) to automate internal review, metadata extraction, and analytical reporting. Integrated generative AI tools into existing business processes: automated document summarisation, structured data extraction from unstructured inputs, and anomaly flagging for compliance workflows. Developed and evaluated ML classification models using statistical image forensics (ELA, ViT, CNNs) to detect forged document regions; iterated on model performance through rigorous evaluation pipelines. Collaborated cross-functionally with engineering and product stakeholders in an agile environment — gathering requirements, iterating on solutions, and documenting technical processes for handover.
Innovating and prototyping new approaches to improve AI models for detecting fraudulent identity documents. Creating, documenting, and evaluating synthetic image datasets generated by LLMs. Testing and benchmarking model performance using real and synthetic datasets to enhance fraud detection accuracy.
Taught game development to students, simplifying coding concepts using block and line-based code. Created and delivered structured lesson plans tailored to different age groups.
Post a job and invite Md, or contact them directly. No hidden commission.
