$ whoami

Anthony Muniz, AI & Backend Engineer

I make LLM agents work with real customers, and I measure it.

Most AI agents look great in a demo and fall apart with real customers. I'm the engineer who finds out why and fixes it, with numbers to prove the fix worked.

  1. The agent tails log files next to each worker.
  2. Batches go to the server over gRPC.
  3. The dashboard updates live over WebSocket.
  4. When an external API keeps failing, healthmon closes the gate on new requests. Retries alone kept hitting a service that was already down.
.log filesagent, Gofsnotify, ring bufferserver, GoJSONL, pub/subdashboardReact, livegRPCWebSockethealthmon: external API error ratenew requestsexternal APIgate opengate closed

$ ls ~/work

  1. 2026

    AI support agent for a B2B SaaS

    It answers customers on WhatsApp, web chat and email. I shipped about 30 releases in 4 weeks, and replies got 3x faster.

    • 3x faster replies
    • ~30 releases in 4 weeks
    • 13 of 23 test questions improved

  2. 2024 to 2026

    Credit analysis pipeline

    I rebuilt a credit fund's manual credit analysis as Python services with queues and workers.

    • about 1 hour down to as little as 5 minutes
    • about 10 to up to 100 operations a day
    • 5+ credit bureaus

  3. Side project

    LogStream

    My first Go project. A sidecar agent streams logs over gRPC to a live dashboard, and healthmon blocks new requests to an external API once its error rate crosses a threshold.

    • Go and gRPC
    • fsnotify and a ring buffer
    • later retired for Grafana

  4. 2026

    RAG side projects

    A PDF notes app and a resume generator on ChromaDB, plus Kai, my personal copilot, with embeddings and cosine similarity in numpy. The bug I remember: every restart wiped the vector index.

    • 1,000-character chunks, 200 overlap
    • duplicates dropped under 0.3 cosine distance
    • 100+ commits on the resume generator

  5. 2023 to 2025

    Tuberculosis surveillance research

    Scrapers for Brazil's public health database feed a dashboard and a forecasting study. No single model won everywhere.

    • MAE 0.0205, the study's best result
    • LSTM, ARIMA, DES and XGBoost compared
    • 67% of cases in men

$ contact anthony

email
anthonympodev@gmail.com
linkedin
linkedin.com/in/anthony-mpo-dev
github
github.com/Anthony-MPO-dev

I'm open to remote backend and AI engineering roles with US and European teams. I also take small freelance projects through my company, Insight AI & Automation.