Pedro Brun00SurfacePT

Senior engineering partner

I build with founders, and help engineering teams put AI into production.

Engagements

  • AI in productionLLM features that ship and stay shipped. Retrieval, agents, evals, fallbacks, observability β€” the messy parts that decide if it survives past the demo.
  • Zero-to-MVPFor founders putting a first version of a product in front of users. Architecture, frontend, backend, deploy β€” owned end to end. AI built in where it earns its place.
  • Architecture reviewOne pair of senior eyes on the plan before it turns into an expensive rewrite. Scaling calls, design reviews, and a written report you can act on.
  • Team trainingAssessmentHands-on training for engineering teams adopting LLMs, agents, and evals. Built on production-ready patterns, not toy examples.

Selected work

  • Voice agent for member networksPlatform with a voice agent that calls the members of a network, holds the conversation and pulls out what each one is after. I built the real-time voice pipeline and the matching that crosses thousands of profiles to find who is worth introducing.
  • AI-driven credit recovery platformThe AI ran the whole negotiation over WhatsApp, 24/7, and closed the agreement with no human in the loop. I co-founded it and closed a contract with over R$11M in receivables.
  • ReclaimiOS app for breaking compulsive habits. It blocks content, tracks progress and answers in chat. I co-founded it and built it end to end.
  • AI investment copilotTracked, in real time, everything B3-listed companies file with the regulator and turned those filings into analysis. I built the ingestion and extraction of the documents and the chat that answers on top of them, anchored to the official filing, across the whole exchange instead of the handful of companies a research shop covers.
  • Kafka event backboneEvent backbone for a live-commerce platform. Four engineering teams adopted it, and it is how their systems talk to each other now.
  • Product ingestion pipelineTakes 500K+ requests a day from partner retailers. Backpressure when they surge, replay when something breaks.

Working on something? Let’s talk.

Putting AI into a product, scaling past a first version that works, or want senior eyes on a plan? Send a paragraph about the project β€” where it is and where it’s stuck.