Who is Pooya Golchian?

Pooya Golchian is an AI Transformation Lead and AI Product Engineer based in Dubai, UAE who takes B2B teams from AI strategy to production. He has shipped software since 2009, with the last three years in production AI, and his work spans agent architecture, MCP servers, RAG pipelines, evals, private LLMs, and AI integrated into Next.js and Node.js stacks. He maintains the open-source packages vue-js-star-rating, vue-multiple-themes, and scss-helper.

What AI services does Pooya Golchian offer?

Pooya Golchian offers AI Engineering (production agent systems, MCP servers, RAG, eval frameworks), Private AI Solutions (on-premise LLM deployment with PDPL and DIFC compliance), AI Team Building (recruitment and structure), and Full-Stack Next.js and Node.js engineering with monorepo experience. He works with GPT-4o, Claude, Gemini, Llama, and Mistral. Available to businesses in Dubai and remotely worldwide.

Is Pooya Golchian available for freelance and remote projects?

Yes. Pooya Golchian is available for freelance, consulting, and remote engagements. Based in Dubai, UAE, he works with clients across the Middle East, Europe, and Asia. He is open to project-based work, monthly retainers, and technical co-founding. Contact him at pooyagolchian.com/contact/ or hello@pooyagolchian.com. He typically replies within 24 hours.

What makes Pooya Golchian's Private AI approach different from typical agencies?

Unlike agencies that route data through third-party cloud APIs, Pooya Golchian deploys AI directly on your own infrastructure: on-premise servers, private cloud, or air-gapped environments. Your data never leaves your network. He specializes in open-source LLMs (Llama, Mistral, Phi) for offline operation, RAG pipelines built on proprietary documents, and custom agents integrated with internal systems. This is especially valuable for finance, healthcare, and legal clients in Dubai and the GCC facing strict data residency requirements.

How can I hire Pooya Golchian for an AI or development project?

Visit pooyagolchian.com/contact/ to send a project inquiry, or email hello@pooyagolchian.com directly. Pooya replies within 24 hours. Engagements start with a free consultation to scope requirements and agree on a timeline. He works with startups, scale-ups, and enterprises in Dubai, the GCC, and globally.

AI Transformation Lead · Agentic AI · Forward Deployed Engineering

AI transformation, shipped from inside your team.

I'm an AI Transformation Lead who embeds with your engineers and puts agentic systems into production. Agents do the heavy lifting. Evals keep them honest. Your team owns the result after I leave.

Book an embedded engagement Start with the Private AI Pilot

Forward deployed, in production

Proof from inside the Cashew brand family.

Cashew · Payments

$10M+/month at 99.99% uptime

Embedded on a live Buy-Now-Pay-Later fintech. I shipped the payment gateway, the fraud layer, and the verification flow.

Hazel Pay

Healthcare-BNPL · Cashew family

Building in-app sales, CRM, and growth agents with Strands on serverless AWS.

See all case studies

The practice

A method, a service, and the tools behind it.

Agentic software engineering is not a buzzword here. It is a documented lifecycle, a way of working with clients, and a real set of Claude Code skills and agents I run every day.

Methodology

AIDLC

The AI Development Life Cycle. Eight phases from a framed problem to an operated, eval-guarded system.

Services

Agentic work

Agentic marketing, development, and systems integration. Production work for operators and founders, not pilots.

Toolkit

Claude Code skills

The skills, agents, and plugins I build to do the work. Filter the catalog by type or browse the full set.

What I Do

Services

Senior engineering for production AI, private LLMs, full-stack systems, and the teams that operate them.

AI Engineering

Production agent systems, MCP servers, RAG, and eval frameworks. Senior engineering for teams shipping AI into real apps.

Private AI Solutions

On-premise LLM deployment with audit-ready architecture. Zero data leakage, PDPL and DIFC ready.

Full-Stack Next.js & Node.js

Production Next.js, Node.js, and monorepo work. Server Components, durable workflows, performance budgets.

Build an AI Team

Hire, train, and structure a senior AI engineering team. Recruitment, interviews, onboarding, and operating cadence.

AI Team Enablement

Train an existing engineering team to ship with agents. Workflow assessment, hands-on AIDLC training, and a rollout plan managers can run.

AWS Infrastructure & Cost Optimization

Migrate from Vercel or Firebase to AWS. Cut hosting costs 40-70% with SST v3, Lambda, CloudFront, and DynamoDB.

Supporting systems

Growth and lifecycle work stays available when it supports an AI product or B2B operator workflow.

MarTech, CRM & Landing Pages

Unified marketing stack, CRM integration, high-converting landing pages, conversion instrumentation.

Data-Driven Email

Lifecycle email programs powered by behavioral data, segmentation, and A/B testing at scale.

Members library

Agentic AI Lab

Members-only writing on how agentic software actually gets built. AIDLC, bolts and specs, AI team building, AWS BFF and serverless, agentic programming, and the skills and plugins behind the workflow.

AIDLC & boltsSpec-drivenAI team buildingAWS BFF · serverlessSkills & plugins

Free

Members only. Sign in to read the full library.

Explore the Lab

Technical Blog

Working notes from shipping agentic AI into production. Agent systems, MCP servers, RAG that cites its sources, evals that catch drift before your customers do, and the AIDLC method I use to move B2B teams past the pilot stage.

Read all posts

Open Source

Open Source Projects

Published npm libraries for Vue, React, SCSS, and Unicode tooling, all open, typed, and documented.

SpecForge

Spec-driven AI development lifecycle with hook-enforced approval gates

Open-source spec-driven AI development lifecycle that fuses Spec Kit and AWS AI-DLC with hook-enforced approval gates.

Fuses GitHub Spec Kit's executable specs with AWS AI-DLC governance
Approval gates enforced by Claude Code PreToolUse hooks, a technical barrier, not advice
Ralph autonomous loop runs an approved plan without inventing new scope
Brownfield reverse-engineering pass documents existing code before any spec is written

Claude CodeAI-DLCSpec KitAgent SkillsDeveloper ToolsGovernance

GitHub Docs

RevOps AI

AI Sales CRM built on Notion with Gemini MCP

Revenue Operations platform where Notion is the database and Gemini 2.5 Flash is the AI sales agent. Kanban pipeline, AI lead scoring, pre-call briefings, and natural language deal management — all powered by 22 Notion operations through the Model Context Protocol.

Notion as the CRM database — no proprietary lock-in, you own your data
Gemini 2.5 Flash autonomously chains 22 Notion MCP operations per request
Drag-and-drop Kanban pipeline synced to Notion in real-time via MCP
One-click AI lead scoring (0–100) with written reasoning, saved to Notion

AINotionMCPNext.jsGeminiCRMRevOps

GitHub Docs

use-local-llm

React hooks for streaming local LLM responses

React hooks for streaming responses from local LLMs — Ollama, LM Studio, llama.cpp, and any OpenAI-compatible endpoint. Direct browser-to-localhost streaming with no server, no API routes, and zero runtime dependencies beyond React.

Direct browser → localhost streaming — no server, no API routes
Multi-backend: Ollama, LM Studio, llama.cpp, OpenAI-compatible
Full chat state — message history, abort, clear, error handling
Token-by-token streaming with onToken callbacks

ReactTypeScriptAILLMOllamaStreaming

$ pnpm add use-local-llm

GitHub npm Docsv1.0.0

See all open source

Work With Me

Hire an AI Engineer for B2B Builds

I design and ship production AI agent teams for B2B companies. Discovery, agent role design, MCP integration, evals, token economics, and deployment.

AI Engineering for B2B

Need an AI agent team that ships for your B2B product?

I join your engineering team and build the agent layer alongside you, covering architecture, MCP integration, evals, and production deployment. When the engagement ends, your team owns the system and keeps shipping.

12+ years shipping production systems

Senior engineer turned AI specialist. React, Next.js, AWS, agent orchestration.

Dubai-based, working with B2B teams worldwide

Direct collaboration across UAE, Europe, and US time zones.

AI agent teams that ship, not demos that stall

Discovery, role design, MCP integration, evals, and production deployment.

Book an embedded engagementOr email hello@pooyagolchian.com to scope a project.

FAQ

About Pooya Golchian

Common questions about Pooya's work, AI services, and how to start a project together.

Pooya Golchian is an AI Transformation Lead and AI Product Engineer based in Dubai, UAE who takes B2B teams from AI strategy to production. He has shipped software since 2009, with the last three years in production AI, and his work spans agent architecture, MCP servers, RAG pipelines, evals, private LLMs, and AI integrated into Next.js and Node.js stacks. He maintains the open-source packages vue-js-star-rating, vue-multiple-themes, and scss-helper.
Pooya Golchian offers AI Engineering (production agent systems, MCP servers, RAG, eval frameworks), Private AI Solutions (on-premise LLM deployment with PDPL and DIFC compliance), AI Team Building (recruitment and structure), and Full-Stack Next.js and Node.js engineering with monorepo experience. He works with GPT-4o, Claude, Gemini, Llama, and Mistral. Available to businesses in Dubai and remotely worldwide.
Yes. Pooya Golchian is available for freelance, consulting, and remote engagements. Based in Dubai, UAE, he works with clients across the Middle East, Europe, and Asia. He is open to project-based work, monthly retainers, and technical co-founding. Contact him at pooyagolchian.com/contact/ or hello@pooyagolchian.com. He typically replies within 24 hours.
Unlike agencies that route data through third-party cloud APIs, Pooya Golchian deploys AI directly on your own infrastructure: on-premise servers, private cloud, or air-gapped environments. Your data never leaves your network. He specializes in open-source LLMs (Llama, Mistral, Phi) for offline operation, RAG pipelines built on proprietary documents, and custom agents integrated with internal systems. This is especially valuable for finance, healthcare, and legal clients in Dubai and the GCC facing strict data residency requirements.
Visit pooyagolchian.com/contact/ to send a project inquiry, or email hello@pooyagolchian.com directly. Pooya replies within 24 hours. Engagements start with a free consultation to scope requirements and agree on a timeline. He works with startups, scale-ups, and enterprises in Dubai, the GCC, and globally.

Loading form

AI transformation, shipped from inside your team.