About me
AI & Full-Stack Engineer passionate about AI and Large Language Models (LLMs), experienced in Generative AI, RAG, MCP servers, and LLM pipelines.
Skilled in designing end-to-end systems for data ingestion, vector stores, prompt engineering, and CI/CD, delivering reliable, cost-efficient AI features for enterprise and consumer applications.
What I'm doing
-
Generative AI
Building and deploying GenAI-powered applications with LLMs.
-
Full-Stack Development
Developing end-to-end systems with modern frameworks and technologies.
-
LLM Pipelines
Designing scalable pipelines for data ingestion, vector stores, and prompt engineering.
-
DevOps & CI/CD
Automating build, test, and deployment cycles with Docker, Kubernetes, and Azure DevOps.