I build LLM-powered applications and autonomous AI agents that solve real business problems: agentic RAG systems that plan and verify their own retrieval, and multi-agent pipelines that automate multi-step workflows end to end.
Over the past 2 years, I've worked on:
- 🎬 Explainer video platform: built a LangChain-based generation system from scratch to production, handling scripting, voiceover, and rendering end to end
- 📞 Voice AI agents: designed and deployed agents that handle real customer conversations end to end in production, from call handling to task completion
- 📚 RAG-based bots: grounded LLM responses in real business data for accurate, up-to-date answers instead of relying on the model's raw memory
I put as much weight on production reliability, evaluation, and cost/latency trade-offs as I do on the initial prototype. A lot of GenAI demos never make it to production, and cutting inference cost without hurting quality is where I focus once something's live.
AI / LLM Engineering
Vector Databases
Backend & Infrastructure
| Project | What it does |
|---|---|
| Transify | Django DRF CRM / all-in-one business platform |
| Elevaiyt | FastAPI-based LLM orchestration service |
| MVAC | MTN Mobile Money API integration |
| Site Vision | YOLO + VLM construction site safety compliance system |
| StreamForge | HLS adaptive video streaming project |
Full write-ups and case studies: faaaizan.space
- Meta Backend Developer Professional Certificate
- Meta Front-End Developer Professional Certificate
- Google UX Design Professional Certificate
I'm currently open to freelance/contract projects and remote full-time roles in AI/GenAI engineering. If you're building an LLM product, need an AI agent built, or want to add GenAI features to an existing app, let's talk.
