Arthur Temporim
AI Engineer at RHEI
São Paulo, Brazil
Summary
🤩
Rockstar🎓
Top SchoolArthur Temporim is an AI Engineer from São Paulo with a decade of experience building production-grade chatbot and conversational AI systems, from NLU optimization to multi-agent LLM orchestration. He has led migrations to Rasa, cut NLU processing time by 90% and doubled intent accuracy, and contributed upstream to the popular open-source Rasa project (including a Rocket.Chat connector and LUIS format improvements). At enterprise scale he designed RAG and Guardrails-backed LLM agents on Amazon Bedrock that slashed customer service costs by 60% and enabled instant knowledge updates. Comfortable across full-stack integrations and containerized deployments, he combines hands-on engineering with research-informed design—holding a master’s focus on conversational agents and gamification—and occasionally shares that expertise through webinars and community chatbot projects.
10 years of coding experience
6 years of employment as a software developer
Master's degree Conversational Agents with gamification, Master's degree Conversational Agents with gamification at Universidade de Brasília
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (19)
apim10
docker10
python10
machine-learning10
dockers10
api10
rasa10
chatterbot10
chatbot10
api-design9
restful-api9
api-rest9
webchat9
rest-api9
nlp9
Programming languages (14)
Github contributions (5)
lappis-unb/rasa-ptbr-boilerplate
Jan 2019 - Nov 2022
Um template para criar um FAQ chatbot usando Rasa, Rocket.chat, elastic search
Role in this project:
Full-stack Developer
Full-stack DeveloperContributions:16 releases, 15 reviews, 401 commits in 3 years 10 months
Contributions summary:Arthur's commits primarily focused on improving the Rasa chatbot boilerplate, enhancing NLU model training, and adding new functionalities. This included removing unnecessary intents, improving the accuracy of the intent classifier, and adding custom action configurations for a Docker setup. Furthermore, the user worked on configuring the webchat, demonstrating expertise in integrating the chatbot with web interfaces.
rasaelasticchatrocketrocket-chat
RasaHQ/rasa
Aug 2018 - Sep 2019
💬 Open source machine learning framework to automate text- and voice-based conversations: NLU, dialogue management, connect to Slack, Facebook, and more - Create chatbots and voice assistants
Role in this project:Back-end Developer
Back-end DeveloperContributions:79 commits, 10 PRs, 110 pushes in 1 year 1 month
Contributions summary:Arthur implemented a Rocket.Chat connector to allow the Rasa chatbot to integrate with Rocket.Chat for text-based conversations. They added functionality to handle incoming messages, send outgoing messages, and manage typing indicators within the Rocket.Chat platform. Furthermore, the user updated the Microsoft LUIS NLU data version and improved the `_is_nlu_format` method to understand more NLU types. They made code changes in `rasa/nlu/training_data/formats/luis.py`, `rasa/data.py`, `rasa/nlu/__init__.py` and other files.
nlupythonbotspeech-recognitionbotkit
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.