Anton Glenbovitch

Senior AI Engineer - Production LLM Systems (RAG, Orchestration, Architecture)
I design and build production-grade AI systems using LLMs and retrieval architectures. My focus is on reliability, performance, and integrating AI into real-world systems - not demos.

Core Focus

  • End-to-end AI system architecture (LLM + RAG)
  • Evaluatable and reliable retrieval pipelines
  • Cost, latency, and performance optimization
  • LLM orchestration and agent workflows
  • Enterprise integration (APIs, data, auth)

Engineering Perspective

In production AI systems, the main challenges are not model selection, but data quality, retrieval accuracy, and system design.

Reliable systems require evaluation, guardrails, and continuous monitoring to control hallucinations and maintain consistency at scale.

Featured Project — Enterprise Claim AI Platform

A production-oriented AI system for insurance claim analysis using RAG architecture, vector retrieval, and LLM reasoning.

Focus areas: retrieval accuracy, system reliability, and scalable AWS deployment.

View Project on GitHub →

Technical Stack

Python • AWS (Bedrock, Lambda, OpenSearch) • Vector DBs • RAG • LLM APIs • REST APIs

Experience

20+ years building enterprise systems at Yale University and as an independent consultant, across backend systems, data platforms, and AI applications.

Links

GitHub LinkedIn