Open to opportunities

shahyan hasan

@shahyanhasan

Message

AI/ML Engineer building production-ready machine learning and Generative AI systems—LLMs, RAG, and agentic workflows.

Pakistan

Message

What I'm looking for

I’m looking for a role where I can build and ship production Generative AI/ML systems—especially LLMs, RAG, and agentic workflows—while owning end-to-end pipelines, deployment, and scalable MLOps practices.

I’m an AI/ML Engineer focused on building production-ready machine learning and Generative AI systems. I work across LLMs, RAG, and agentic AI, with an end-to-end mindset that spans data pipelines, model development, and deployment.

In my recent experience, I’ve built web scraping pipelines and conversational memory systems using hybrid search to extract structured data and manage user-agent interaction history. I’ve also designed semantic search and RAG pipelines with vector embeddings, building self-service AI agents using LangChain, LangGraph, and GraphRAG.

I bring a strong software engineering foundation to real-world AI delivery, building and shipping supporting systems with FastAPI, Docker, Kubernetes, and MLflow. Through my projects—like end-to-end ML deployments and LLM-powered assistants—I’ve learned to prioritize scalability, reliability, and clear orchestration from experiment tracking to production serving.

Experience

Work history, roles, and key accomplishments

Current

AI Intern

Current

Systems Limited

Jan 2025 - Present (1 year 7 months)

Built web scraping pipelines and conversational memory systems using hybrid search to extract structured data and manage user-agent interaction history. Designed semantic search and RAG pipelines with vector embeddings and contributed to agentic AI using LangChain, LangGraph, and GraphRAG.