Temirlan Dzhoroevbuilds AI that ships.
I build the parts of an AI product that have to survive contact with real users — hybrid RAG that actually recalls, agent orchestration you can reproduce, guardrails that run before you pay for a token, and the gateway underneath keeping it all alive. Six production systems below, reaching over ten million people.
Selected
work
Six systems running in production — hybrid RAG with reranking, agent orchestration, streaming codegen, and a platform that reached ten million users. Open any card for the full case study.
Enterprise Agent Platform
Hybrid parsing, hybrid retrieval, cross-encoder reranking — and an agent per tenant on top.
Companion Chat Runtime
A real-time AI companion that remembers, reacts in its own voice, and moves the scene.
Prompt to Playable
Type an idea, watch a playable game build itself — in the browser, mid-stream.
PDF to Lesson
A textbook PDF becomes an interactive lesson — generated multimodally, moderated for the room it runs in.
Model Gateway
The serving layer under both products — routing, moderation, caching, and back-pressure.
3D Studio
A browser 3D game studio that reached 10M users — block scripting, authoritative multiplayer, in-editor AI.
A bit
about me.
One person, three disciplines, and an obsessive standard for craft.
Research, engineering, and product held in a single head — so ideas ship as fast as they’re proven.
I help founders and teams take AI from prototype to production — the messy middle where demos meet real users, latency, cost, and evals. No hand-waving: measurable systems that hold up.
I care about models that are correct, fast, and honest about their limits. The best AI feels less like magic and more like a tool you can actually trust.
Agent Orchestration
LangGraph runtimes, tool registries, checkpointed state, and control flow you can reproduce.
RAG & Retrieval
Hybrid dense + lexical search, structure-aware ingestion, reranking, and ACL inside the query.
LLM Infrastructure
Gateways, key pools, fallback chains, semantic caching, and streaming that survives real load.
Evals & Guardrails
Golden sets, LangSmith tracing, layered guardrails, and the observability to prove any of it.
Proof of
craft.
Credentials earned along the way — the coursework and exams behind the practice.
Agentic AI
Advanced RAG with Vector Databases and Retrievers
Vector Databases for RAG: An Introduction
Foundation — Introduction to LangChain (Python)
Develop Generative AI Applications: Get Started
Build RAG Applications: Get Started
Gen AI Agents: Transform Your Organization
Principles of UX/UI Design
Advanced React
Algorithmic Toolbox
Korean Language, 3rd Level
Words from the
people who shipped it.
“They turned our pile of docs into an assistant that actually answers correctly — shipped in weeks, and the evals prove it.”
“Rare to find an engineer who gets both the model and the product. Our agent went from a flaky demo to dependable in production.”