Luís Guilherme

Senior Software Engineer | Distributed Systems & AI Architect Remote (Brazil Based) · lgpelin92@gmail.com · github.com/lguibr · luisguilher.me

PROFESSIONAL SUMMARY

Senior Software Engineer bridging the gap between theoretical complexity (Physics background) and production reliability. Specializing in Agentic AI workflows, High-Frequency Trading interfaces, and Distributed Actor Models. I build tools that build software. From architecting multi-agent negotiation protocols at YC startups to writing custom MCTS engines in C++, I ˝deliver systems that are mathematically sound and commercially scalable.

TECHNICAL ARSENAL

  • Core Stack: TypeScript (Expert), Python (Advanced), Go (Systems), C++ (Engine).
  • AI & Data: LLM Orchestration (LangChain/Claude), RAG Pipelines, AlphaZero/MCTS, PyTorch, Vector Search.
  • Infrastructure: AWS (ECS/Lambda), GCP, Terraform, Docker, Kubernetes, Ray (Distributed Compute).
  • Architecture: Event-Driven Systems, Actor Models, Microservices, Real-time WebSockets.

PROFESSIONAL EXPERIENCE

Trebu (YC S22) | AI Software Engineer Jul 2024 – Nov 2025 Architected the autonomous logistics negotiation engine for a high-growth YC startup.

  • Multi-Agent Orchestration: Designed and shipped the Find Me a Truck protocol, an autonomous multi-agent system that negotiates pricing with truckers via WhatsApp, replacing manual operations.
  • Latency Optimization: Reduced LLM pipeline latency by 66% through parallel execution trees, semantic caching, and aggressive prompt engineering.
  • Business Impact: Slashed end-to-end negotiation time from 3+ minutes to <60 seconds, directly increasing booking conversion rates.
  • Computer Vision: Integrated SAM (Segment Anything Model) into the OCR pipeline, improving document parsing accuracy by 6% for non-standard logistics paperwork.

Paradigm | Software Engineer (High-Frequency Trading) Apr 2022 – Apr 2024 Engineered mission-critical frontend systems for the world’s largest institutional crypto derivatives network.

  • Performance Engineering: Built low-latency trading interfaces (sub-second updates) capable of handling millions in daily volume without rendering lag.
  • System Unification: Consolidated three disparate codebases (React Web, React Native, Electron) into a single monorepo architecture, reducing feature delivery time by 40%.
  • Reliability: Implemented critical-path E2E testing (Playwright) for trade execution flows, preventing regression in financial logic.

Trio | Tech Lead May 2020 – Apr 2022 Technical leadership for multiple squads, delivering enterprise solutions for brewery and traceability clients.

  • Architecture & Scale: Led the migration from monolithic structures to scalable microservices on GCP/AWS using Terraform.
  • Leadership: Mentored 8+ developers, introducing strict code review standards and CI/CD pipelines that reduced deployment failures to near zero.

SELECTED ENGINEERING PROJECTS

Projects demonstrating Systems Thinking & Architecture.

Pongo (Go, WebSockets, Actor Model)

  • What it is: A distributed, real-time multiplayer game engine.
  • The Tech: Built a custom Actor Model library (Bollywood) from scratch in Go to handle high-concurrency state management without race conditions. Achieved zero-dependency architecture for maximum performance.
  • Live: pongo.luisguilher.me

AlphaTriangle (Python, Ray, C++, PyTorch)

  • What it is: An AlphaZero-style AI agent trained via distributed self-play.
  • The Tech: Implemented Monte Carlo Tree Search (MCTS) in C++ for performance, wrapped in Python for training. Orchestrated distributed training jobs using Ray to scale self-play simulations across cores.
  • Live: tricrack.luisguilher.me

MimeFlow (TypeScript, TensorFlow.js, WebGL)

  • What it is: Browser-based computer vision engine for pose estimation.
  • The Tech: Utilizes 5D vector cosine similarity to calculate movement accuracy against video feeds in real-time, running entirely on the client-side GPU via WebGL.
  • Live: mimeflow.luisguilher.me

LuisGuilher.me (Next.js, Virtual File System)

  • What it is: A portfolio that simulates a complete Operating System / IDE.
  • The Tech: Engineered a Virtual File System (VFS) and window manager in the browser. Features a fully functional code editor (Monaco) and command-line interface.

EDUCATION

Universidade Federal de Minas Gerais (UFMG) Undergraduate Studies in Physics (2018–2022)

  • Focus: Computational Physics, Complex Systems, Linear Algebra, and Calculus.
  • Pivoted to full-time Software Engineering to apply computational models to production systems.

CEFET-MG Technical Degree in Information Technology (2006–2008)

Luís Guilherme

Luís Guilherme

Senior Software Engineer | Distributed Systems & AI Architect Remote (Brazil Based) · lgpelin92@gmail.com · github.com/lguibr · luisguilher.me

PROFESSIONAL SUMMARY

Senior Software Engineer bridging the gap between theoretical complexity (Physics background) and production reliability. Specializing in Agentic AI workflows, High-Frequency Trading interfaces, and Distributed Actor Models. I build tools that build software. From architecting multi-agent negotiation protocols at YC startups to writing custom MCTS engines in C++, I ˝deliver systems that are mathematically sound and commercially scalable.

TECHNICAL ARSENAL

  • Core Stack: TypeScript (Expert), Python (Advanced), Go (Systems), C++ (Engine).
  • AI & Data: LLM Orchestration (LangChain/Claude), RAG Pipelines, AlphaZero/MCTS, PyTorch, Vector Search.
  • Infrastructure: AWS (ECS/Lambda), GCP, Terraform, Docker, Kubernetes, Ray (Distributed Compute).
  • Architecture: Event-Driven Systems, Actor Models, Microservices, Real-time WebSockets.

PROFESSIONAL EXPERIENCE

Trebu (YC S22) | AI Software Engineer Jul 2024 – Nov 2025 Architected the autonomous logistics negotiation engine for a high-growth YC startup.

  • Multi-Agent Orchestration: Designed and shipped the Find Me a Truck protocol, an autonomous multi-agent system that negotiates pricing with truckers via WhatsApp, replacing manual operations.
  • Latency Optimization: Reduced LLM pipeline latency by 66% through parallel execution trees, semantic caching, and aggressive prompt engineering.
  • Business Impact: Slashed end-to-end negotiation time from 3+ minutes to <60 seconds, directly increasing booking conversion rates.
  • Computer Vision: Integrated SAM (Segment Anything Model) into the OCR pipeline, improving document parsing accuracy by 6% for non-standard logistics paperwork.

Paradigm | Software Engineer (High-Frequency Trading) Apr 2022 – Apr 2024 Engineered mission-critical frontend systems for the world’s largest institutional crypto derivatives network.

  • Performance Engineering: Built low-latency trading interfaces (sub-second updates) capable of handling millions in daily volume without rendering lag.
  • System Unification: Consolidated three disparate codebases (React Web, React Native, Electron) into a single monorepo architecture, reducing feature delivery time by 40%.
  • Reliability: Implemented critical-path E2E testing (Playwright) for trade execution flows, preventing regression in financial logic.

Trio | Tech Lead May 2020 – Apr 2022 Technical leadership for multiple squads, delivering enterprise solutions for brewery and traceability clients.

  • Architecture & Scale: Led the migration from monolithic structures to scalable microservices on GCP/AWS using Terraform.
  • Leadership: Mentored 8+ developers, introducing strict code review standards and CI/CD pipelines that reduced deployment failures to near zero.

SELECTED ENGINEERING PROJECTS

Projects demonstrating Systems Thinking & Architecture.

Pongo (Go, WebSockets, Actor Model)

  • What it is: A distributed, real-time multiplayer game engine.
  • The Tech: Built a custom Actor Model library (Bollywood) from scratch in Go to handle high-concurrency state management without race conditions. Achieved zero-dependency architecture for maximum performance.
  • Live: pongo.luisguilher.me

AlphaTriangle (Python, Ray, C++, PyTorch)

  • What it is: An AlphaZero-style AI agent trained via distributed self-play.
  • The Tech: Implemented Monte Carlo Tree Search (MCTS) in C++ for performance, wrapped in Python for training. Orchestrated distributed training jobs using Ray to scale self-play simulations across cores.
  • Live: tricrack.luisguilher.me

MimeFlow (TypeScript, TensorFlow.js, WebGL)

  • What it is: Browser-based computer vision engine for pose estimation.
  • The Tech: Utilizes 5D vector cosine similarity to calculate movement accuracy against video feeds in real-time, running entirely on the client-side GPU via WebGL.
  • Live: mimeflow.luisguilher.me

LuisGuilher.me (Next.js, Virtual File System)

  • What it is: A portfolio that simulates a complete Operating System / IDE.
  • The Tech: Engineered a Virtual File System (VFS) and window manager in the browser. Features a fully functional code editor (Monaco) and command-line interface.

EDUCATION

Universidade Federal de Minas Gerais (UFMG) Undergraduate Studies in Physics (2018–2022)

  • Focus: Computational Physics, Complex Systems, Linear Algebra, and Calculus.
  • Pivoted to full-time Software Engineering to apply computational models to production systems.

CEFET-MG Technical Degree in Information Technology (2006–2008)

luisguilher.me - Visual Profile Code

|

Made with ❤️