About
Full-stack engineer building multi-tenant SaaS and production AI features
I'm a full-stack engineer with 5+ years shipping production Ruby on Rails, Python/FastAPI, React and Node.js applications for international product teams. I build multi-tenant SaaS platforms and production AI features, including real-time voice agents, LLM tool calling, transcript pipelines and vector search, behind provider-agnostic abstractions so they survive vendor changes. At Xprolabs I've worked closely with solution architects, UX designers and systems analysts on cross-brand modules for the Traton group (MAN and Navistar). I own features end to end, mentor junior engineers, and drive the CI/CD and code-review standards that shorten release cycles.
Ship end to end
From the data model to the deployed interface, across Rails, FastAPI, NestJS, React and Next.js.
AI in production
Real-time voice agents, LLM tool calling, transcript pipelines and vector search, behind provider-agnostic abstractions.
Quality gates
CI/CD pipelines, automated tests and code-review standards that shorten release cycles.
How I work
The backend is the boundary
Every request resolves its tenant and role on the server before a scoped query runs, so a tenant only ever sees its own data.
Providers behind one switch
Voice and LLM providers sit behind one abstraction, so changing vendors doesn't mean a rewrite or downtime.
Money paths are idempotent
Billing runs carry an idempotency key, so a retried run produces one invoice, never two.
Root cause, tests, gated deploy
Audit, fix the root cause, add tests that prove it, and ship through a CI-gated pipeline.
Building a SaaS product with AI in it?
From the data model to the deployed interface: multi-tenant platforms, AI voice agents, LLM features and Stripe billing.