# Raza Jahangir

> AI Systems Engineer in Lahore, Pakistan. Freelance AI systems engineer building production AI agents, RAG pipelines, and private LLM deployments. 13+ years of backend engineering.

I help teams put multi-agent applications, retrieval-augmented generation pipelines, and private, open-weight models into production, and keep them working after launch.

The full site as one Markdown file, including every case study: https://razajahangir.dev/llms-full.txt

## Services

- AI agent development: Single and multi-agent applications with tool calling, state, and limits on what the model may do, built with LangGraph.
- RAG pipeline development: Retrieval-augmented generation over your own documents, with citations, built with LlamaIndex and PostgreSQL + pgvector.
- Private and self-hosted LLM deployment: Open-weight models on your own hardware through Ollama or vLLM behind a private gateway, with no outbound calls to third parties.
- LLM evaluation and monitoring: Test sets from your real data before release, then tracing, dashboards, and alerts for quality, cost, and latency once it is live.

## Pages

- [Home](https://razajahangir.dev/): Freelance AI systems engineer building production AI agents, RAG pipelines, and private LLM deployments. 13+ years of backend engineering.
- [About](https://razajahangir.dev/about/): Background, stack, work in progress, and answers to common questions.
- [Common questions](https://razajahangir.dev/about/#faq): What I do, private and self-hosted AI, evaluation, tools, location, and how to hire me.
- [Work](https://razajahangir.dev/work/): Selected AI systems, with the architecture and the result of each one.
- [Approach](https://razajahangir.dev/approach/): Build, evaluate, deploy, and monitor.
- [In-house AI](https://razajahangir.dev/work/inhouse-ai/): A self-hosted assistant for teams that need chat and document Q&A without sending files to a third-party model. DOCKER · OLLAMA · LITELLM · PGVECTOR · CLOUDFLARE TUNNEL
- [In-house AI source](https://github.com/razajahangir/inhouse-ai)
- [Atlas Planner](https://razajahangir.dev/work/atlas-planner/): AI goal planning for a coaching membership. Members assess life and business, then get focus areas, goals, and scheduled actions from the client's own library. WORDPRESS · PHP 8.1 · OPENAI · JSON SCHEMA · RAG
- [DraftCraft](https://razajahangir.dev/work/draftcraft/): Scheduled blog drafts for WordPress, in the site's own voice, held for review before anything is published. FREE & OPEN SOURCE · GPL v2+ · WORDPRESS.ORG
- [DraftCraft source](https://github.com/ArtisansWP/DraftCraft)
- [Custom GPT Manager](https://razajahangir.dev/work/custom-gpt-manager/): Several chat agents from wp-admin, each with its own prompt, model, knowledge base, and access rules, embedded with a shortcode. WORDPRESS · PHP · JAVASCRIPT · OPENROUTER
- [Intelara](https://razajahangir.dev/work/intelara/): A private AI chat workspace that keeps projects, threads, files, notes, and tools together, with your own OpenRouter key and a spend cap on every project. NEXT.JS 16 · REACT 19 · SUPABASE · OPENROUTER · MCP
- [AgenticLearn](https://razajahangir.dev/work/agenticlearn/): A tutor that helps developers close a specific gap, instead of sending them through a full course. FASTAPI · LANGGRAPH · DEEPSEEK · GEMINI · TAVILY · POSTGRES
- [devnull-tui](https://github.com/razajahangir/devnull-tui): A terminal client for dev-null.sh. Feeds, threads, profiles, and compose, with requests signed for the /api/v1 API.

## Profiles

- [LinkedIn](https://www.linkedin.com/in/raza-jahangir)
- [GitHub](https://github.com/razajahangir)
- [X](https://x.com/developerRaza)
- [Substack](https://razajahangir.substack.com)
- [YouTube](https://www.youtube.com/@razajahangir)
- [Upwork](https://www.upwork.com/freelancers/developerraza)

## Optional

- [Privacy](https://razajahangir.dev/privacy/)
- [Terms](https://razajahangir.dev/terms/)
- [Disclaimer](https://razajahangir.dev/disclaimer/)