hi, I'm Adnan Rahmanpoor

Applied AI Engineer.

I build production AI systems and data products - from evaluation infrastructure, semantic caching, and multi-agent orchestration to a live Dubai real estate intelligence platform processing millions of DLD transactions end to end.

AI SYSTEMS · AGENTIC WORKFLOWS · DATA PRODUCTS · AI-NATIVE DEVELOPMENT

97% latency reduction • pgvector cache
4 concurrent AI agents
Static JSON • zero cold starts
Distributed eval pipeline • Celery + Redis
97% latency reduction • pgvector cache
4 concurrent AI agents
Static JSON • zero cold starts
Distributed eval pipeline • Celery + Redis

Systems

LLM Gateway & Caching

AI Control Plane

A unified LLM gateway: semantic caching with pgvector cuts response latency by up to 97% on repeated queries, a prompt registry enables weighted A/B rollouts without redeploys, and a background AI-SRE agent diagnoses latency anomalies and pages Telegram with root-cause analysis before a human notices.

FastAPIPostgreSQLpgvectorRedisDockerTelegram API
LLMOps / Evaluation

AI Eval Platform

A CI/CD pipeline for LLMs. Celery workers run prompt evaluations against golden datasets at scale, an anti-sycophancy LLM-judge grades business accuracy instead of instruction-following, and full OpenTelemetry tracing through Jaeger pinpoints whether a slowdown is Postgres, Redis, or the model API — down to the millisecond.

FastAPICeleryRedisPostgreSQLOpenTelemetryJaegerDocker
Real Estate Data Platform

GetPropIntel

An independent, DLD-data-driven intelligence platform for Dubai real estate. A DuckDB pipeline unifies historical and daily transaction schemas, computes rental yield, momentum, and liquidity scoring per area, and pre-renders everything to static JSON served through Next.js — no live backend, no cold starts.

PythonDuckDBNext.jsSQL
Multi-Agent Orchestration

Crypto Research Agent

Four specialized agents — technical, market, news, sentiment — run concurrently via native asyncio and synthesize into a single hedge-fund-style investment report. Built without LangGraph or CrewAI by design: a custom orchestrator kept the container lightweight and gave full control over failure handling.

FastAPIPython asyncioCoinGecko APIDocker

How I Build

I use AI coding agents - Claude Code, ChatGPT, Deepseek and Qwen - as a core part of my development workflow. They accelerate implementation; I own the architecture, trade-offs, debugging, evaluation, and production decisions.

AI-Accelerated

Implementation, boilerplate, first-pass code

Human-Owned

Architecture, trade-offs, debugging

Result

4 shipped systems, solo

Stack

AI & Agent Systems

LLMsAgentic WorkflowsLLM EvaluationPrompt EngineeringSemantic CachingMulti-Agent Systems

Data & ETL

PythonDuckDBSQLPostgreSQL

Backend & Infrastructure

FastAPIRedisCelerypgvectorDocker

Observability

OpenTelemetryJaeger

Frontend

Next.jsTailwind CSS

AI Development

Claude CodeChatGPTQwenDeepseek

Background

I started in business and finance, a degree in Management and Finance from Ajman University - rather than computer science. That background shapes how I build: I start with the problem, understand the constraints, and then choose the technology.

Before AI infrastructure, I worked in Dubai real estate market analytics and client-facing property advisory, which is where GetPropIntel came from a need I understood firsthand, not a hypothetical one.

Currently: Dubai, UAE

Get in Touch

Building an AI product, intelligent system, or data platform? Let's talk.

AI SYSTEMS · AGENTIC WORKFLOWS · DATA PRODUCTS · AI-NATIVE DEVELOPMENT