AI Engineer • Machine Learning Systems • Python Developer

I am an AI Engineer specializing in autonomous agent architectures, dual-LLM systems, and high-throughput semantic routing. My focus is on building deterministic, production-ready AI infrastructure that bridges the gap between raw LLM capabilities and reliable enterprise execution.

My expertise lies in bypassing traditional LLM limitations—whether through engineering secure LangGraph multi-agent systems, deploying Retrieval-Augmented Generation (RAG) loops with vector databases, or building zero-shot INT8 ONNX embeddings to eliminate token costs and latency. I don't just prompt models; I build the robust backend engines that orchestrate them.

• Agentic Architecture: Dual-LLM Drafter-Critic loops, LangGraph, Human-in-the-Loop (HITL) constraints, RCE/SSRF security.
• AI Infrastructure: Asyncio, FastAPI, Dynamic Batching, ONNX Runtime.
• NLP & Vector Search: ChromaDB, Custom Embeddings, Dense Retrieval, Semantic Routing.
• Machine Learning: Supervised/Unsupervised Pipelines, Scikit-learn, Deterministic Evaluators.

Languages & Frameworks

AI & Machine Learning

Data & Analytics