Andrey Keske is an AI engineer specializing in production-grade retrieval-augmented generation (RAG) and full-stack AI infrastructure, with 11 years of experience building reliable, evaluation-friendly LLM systems. He designs deterministic ingestion pipelines, embedding/versioning strategies, and multi-tenant-safe retrieval stacks that prioritize grounded answers and reproducibility. As a former founding full-stack engineer and startup CTO, he brings product-first instincts to infrastructure work—shipping node-based workflow studios, canvas-scoped retrieval UIs, and secure API surfaces. His implementations emphasize operational maturity (observability, background indexing, provider fallbacks) and safe upgrade paths (re-index loops, embedding versioning) that minimize data loss. Based in Miami Beach, he blends deep front-end craftsmanship from mobile and React migrations with backend systems expertise (FastAPI, Qdrant, Postgres, Celery) to move LLM prototypes into production. An underappreciated strength is his focus on deterministic, re-index-safe chunking and metadata-preserving ingestion that makes long-lived knowledge systems auditable and upgradeable.
11 years of coding experience
7 years of employment as a software developer
Bachelor's degree, Design, Bachelor's degree, Design at Ural State Pedagogical University
Contributions:56 commits, 42 pushes, 2 branches in 2 years 6 months
javascriptreacttypescript
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.
Request Free Trial
Andrey Keske - AI Engineer (RAG Full-Stack Systems) at Dokka