I'm Roshaan Ejaz. I build AI systems for companies that sell and manage property, and I stay on to run them.
I came to this through engineering, not marketing: a computer science degree, then years building automation and machine learning systems in-house before going independent. That's why the work survives contact with production. I care about the parts nobody demos — what happens when a provider rate-limits you at 4pm, whether your calling setup is legal where you're calling, and who owns the account when the engagement ends.
Property is a business of fast follow-up in more than one language, which is exactly what these systems are good at. I work with a small number of clients at a time, across the US, Europe and Pakistan.
Earlier engineering work
Where the retrieval and evaluation habits came from.
Not real estate, but it is the reason the AI half of this work is the half I worry about least.
- A retrieval system over clinical documents using LangChain and FAISS.
- Transformer models for code generation and summarisation in PyTorch.
- An automated unit-test generator for Java, evaluated across 50+ programs, built as a final-year research project.
Before going independent I spent years building automation and machine learning systems in-house, which is where the production instincts came from: rate limits, retries, provider outages, and the difference between a demo that works once and a system that works on a Tuesday afternoon.
How I work
Two engagements at a time, US and European hours, and a written handover at the end of every one. The systems run on your accounts, with your API keys, under your billing, from day one — so if you want to move the work in-house or to another vendor, nothing about my setup makes that hard.
Tell me what happens to your leads today.
Roughly how many enquiries you get a month, and what happens to the ones nobody calls back. Thirty minutes. If I'm not the right person for it, I'll say so on the call and point you somewhere better.