I'm a 20-year-old AI/ML Engineer focused on production-grade LLM applications, autonomous agents, and RAG pipelines. I go beyond APIs to make language models work in automated, beneficial ways.
"Complexity is the failure of imagination. Power lies in the brutal simplification of the impossible."
Building production systems that make a real impact.
Current Role
I develop production-grade LLM applications, successfully deploying a personalized Resume Scoring System and contributing to core agentic workflows. I'm gaining deep hands-on experience with token optimization, latency reduction, and the internal mechanics of modern transformers.
Specialized in systems that think, retrieve, and scale.
Designing systems that plan, reason, and execute actions independently. From browsing the web to managing complex email workflows.
Architecting pipelines connecting LLMs to private knowledge bases with high-accuracy retrieval using vector databases and semantic reranking.
Building robust APIs with Flask/FastAPI, wrapped in Dockerized microservices designed for production stability and easy deployment.