Building intelligent systems with LLMs, RAG pipelines, and MLOps — turning complex AI research into production-ready applications.
I’m an AI Engineer with 4+ years of experience building production-grade AI platforms, specializing in Generative AI, agentic workflows, and scalable ML systems. I hold an MS in Artificial Intelligence.
I design and deploy end-to-end AI solutions — from fine-tuning foundation models and architecting RAG pipelines to building FastAPI services, AI agents with tool calling, and cloud-native MLOps workflows. My work spans AWS (Bedrock, Lambda, ECS), LangChain/LangGraph, vector databases,Langfuse for observability and full-stack deployment of LLM-powered applications.
Recently, I’ve built voice assistants, LLM evaluation APIs, and knowledge-aware AI systems that operate reliably in real production environments.
I’m passionate about pushing the boundaries of what AI can do and translating cutting-edge research into real-world impact. I enjoy solving complex problems at the intersection of AI engineering, system design, and applied research — turning experimental models into scalable, user-facing products.
End-to-end RAG system to analyze and answer questions on developer documentation using vector embeddings and LLM generation.
Experimenting with the CrewAI Agent Framework for multi-agent orchestration and autonomous task execution.
Automated research pipeline with 5 specialized agents, Gradio web interface, and structured outputs using Pydantic.