Open to opportunities

Matheus Silva

@matheussilva1

Product-minded Software Engineer specializing in AI platforms and agentic systems, with 7+ years of experience across backend engineering, applied AI,

Brazil

Message

What I'm looking for

I'm seeking roles building production-grade conversational AI and data systems end-to-end, emphasizing scalable low-latency performance, RAG and knowledge-graph explainability, Rust for performance-critical components, and collaborative, product-focused teams.

I build AI systems that have to work in production: agents that execute reliably, platforms that other engineers can build on, and LLM-powered products whose quality, latency, cost, and failures can actually be measured.

I am a software engineer with over seven years of experience across backend engineering, applied AI, research, data platforms, and LLMOps. My strongest area is turning promising AI prototypes into reliable product and platform capabilities.

At Housecall Pro, I work on an AI platform serving more than 60,000 monthly users. I designed and built a distributed scheduler for autonomous agents and reusable skills, including concurrency controls, retries, organization-scoped authentication, run-history APIs, observability, and end-to-end validation. I have also worked on long-term agent memory and context reconstruction, isolated Kubernetes runtimes, sandboxed execution, developer tooling, and production reliability. Recent infrastructure improvements reduced Redis CPU usage by approximately 5× and key-command latency by approximately 8×.

My applied AI experience includes production Text-to-SQL systems, RAG and GraphRAG, MCP-based tool orchestration, multi-agent architectures, LLM evaluation, and real-time voice agents. I helped replace a monolithic voice AI implementation with a system of specialized agents supporting approximately 20,000 calls per month. I also led the development of an SRE investigation agent that reduced alert investigation time from over 30 minutes to under five.

What differentiates me is the combination of AI depth and strong software engineering fundamentals. I can work on agent behavior, context engineering, retrieval, and evaluation, but I am equally comfortable reasoning about distributed execution, APIs, databases, observability, Kubernetes, failure recovery, and the operational constraints that determine whether an AI system is actually production-ready.

I also hold a master’s degree focused on Generative AI, have first-authored research on evaluating database conversational agents, and regularly teach AI engineering and agentic software development.

I am based in Rio de Janeiro, Brazil, with experience working in distributed international teams. I am looking for a remote, hands-on senior or staff-level role where I can own meaningful technical problems across Applied AI, AI platforms, agent infrastructure, or developer tools, working as an international contractor.

Experience

Work history, roles, and key accomplishments

Current

Software Engineer — AI Platform & LLMOps

Current

Housecall Pro

Feb 2026 - Present (6 months)

Expanded an AI platform serving 60K+ monthly users by designing and building ai-scheduler, a Go service with distributed execution, organization-scoped authentication, retry and concurrency controls, run-history APIs, Datadog metrics, and end-to-end tests. Reduced Redis engine CPU by ~5x and key-command latency by ~8x, and cut Datadog alert investigation time from 30+ minutes to under 5 minutes.

Redis PostgreSQL Kubernetes Docker Datadog Langsmith GitLab CI CD ECR Vault MCP AI Agents LLMOps Distributed Systems Observability

Current

AI Engineering Instructor & Ambassador

Current

Borderless Coding

Feb 2025 - Present (1 year 6 months)

Recurring invited instructor teaching AI engineering and agentic software development, including LLM agents, AI-assisted coding workflows, agent skills, plugins, hooks, and developer tooling. Conduct AI System Design mock interviews and mentor Brazilian technology professionals.

AI Engineering Agentic Software Development LLM Agents AI Assisted Coding Mentorship System Design

Software Engineer — Voice AI & Multi-Agent Systems

Simbie AI

Sep 2025 - Mar 2026 (6 months)

Supported ~20K voice calls per month by replacing a monolithic Retell AI prompt wrapper with a TypeScript backend orchestrating four specialized agents through explicit routing and handoffs. Built real-time WebSocket integration with Retell AI's telephony layer and implemented Grafana-based observability for voice-agent sessions.

TypeScript WebSockets Retell AI Multi Agent Systems Grafana Observability Backend Development

AI & Data Engineer

BTG Pactual

Mar 2024 - Sep 2025 (1 year 6 months)

Eliminated engineer-handled analytics tickets by building a production Text-to-SQL agent with PostgreSQL-defined LangGraph workflows served through FastAPI. Built an MCP orchestration layer, implemented RAG and GraphRAG strategies, and shipped an offline LLM evaluation pipeline with release guardrails.

Python fastAPI PostgreSQL LangGraph MCP RAG Graph RAG LLM Evaluation AWS Step Functions AWS Lambda Event Driven Architecture

Research Software Engineer

Tecgraf Institute · PUC-Rio

Apr 2023 - Mar 2024 (11 months)

Enabled thousands of Petrobras engineers to query industrial databases through natural language by productizing Text-to-SQL research into an internally deployed conversational agent. First-authored research on automated evaluation of database conversational agents and co-authored work on industrial Text-to-SQL.

Text To SQL Conversational Agents Research Knowledge Graphs Multimodal Integration Python

Software Engineer — Backend & Applied AI

cogg.ai

Mar 2020 - Apr 2023 (3 years 1 month)

Built and maintained Python and AWS backend services, APIs, and data workflows for client products, including recommendation systems and conventional web applications. Developed early LLM-powered chatbot systems using OpenAI APIs during the initial adoption of ChatGPT.

Python AWS Backend Development REST APIs Data Workflows OpenAI Chatbot Recommendation Systems

Software Engineering Intern

cogg.ai

Mar 2019 - Mar 2020 (1 year)

Contributed to backend services, APIs, and data workflows for client products, including recommendation systems and web applications. Progressed from intern to full-time software engineer.

Python AWS Backend Development REST APIs Data Workflows

Education

Degrees, certifications, and relevant coursework

Pontifical Catholic University of Rio de Janeiro

Master of Science, Computer Science (Agent Engineering)

2024 - 2025

Activities and societies: Master's thesis work on dialogue dataset generation and evaluation; related code: https://github.com/MatheusOliveiraSilva/dialogue-dataset-generator

Completed a Master of Science in Computer Science focused on agent engineering, conducting thesis work on dialogue dataset generation and evaluation for conversational database agents.