João Hluchan
Software Engineer at NUTES - UEPB UNIDADE EMBRAPII
Paraíba, Brazil
Summary
🤩
Rockstar🎓
Top SchoolJoão Hluchan is a backend-focused software engineer with six years of experience building resilient, production-grade services using Python, Node.js and Rust. Based in Paraíba, Brazil, he has a strong track record in healthcare and public-sector projects, from RAG-based assistants and microservices to a tax-assessment classification service that incorporates self-training predictive models. An active open-source contributor, João helped enhance Langflow’s backend—improving vector store integrations (Redis, MongoDB Atlas, Cassandra, Couchbase) and securing model configs for HuggingFace—showing his ability to bridge ML tooling and infra. He frequently optimizes performance-critical paths with Rust (via FFI/PyO3) and builds reliable messaging layers, exemplified by an AMQP client that improves RabbitMQ reconnection and resilience. João combines practical engineering craftsmanship with a knack for turning research-oriented AI components into maintainable, scalable backend systems.
6 years of coding experience
4 years of employment as a software developer
Bachelor's Degree in Computer Science, Computer Science, Bachelor's Degree in Computer Science, Computer Science at Universidade Estadual da Paraíba
Github Skills (11)
backend10
back-end-development10
python10
langchain10
large-language-models9
api8
apidoc8
generative-ai8
docker6
dockers6
agent5
Programming languages (5)
Github contributions (5)
langflow-ai/langflow
May 2024 - Aug 2024
Langflow is a low-code app builder for RAG and multi-agent AI applications. It’s Python-based and agnostic to any model, API, or database.
Role in this project:
Back-end Developer
Back-end DeveloperContributions:5 reviews, 9 PRs, 2 pushes in 2 months
Contributions summary:João primarily contributed to the backend infrastructure, focusing on the integration and management of various vector stores. They made adjustments to Redis and MongoDB Atlas vector stores, and updated the format of multiple vector store components, including Cassandra, Couchbase, and others. Additionally, they implemented changes related to model configurations and dependencies, specifically for HuggingFace models, ensuring that sensitive information is securely stored.
chatgptgenerative-ailarge-language-modelsreact-flow
berrytern/Discord
Apr 2020 - Mar 2024
Contributions:71 pushes, 6 branches in 3 years 11 months
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.