Gianluca Silvestri is a Data Scientist with 8 years of experience, currently working at IBM and pursuing PhD-level research in machine learning at OnePlanet Research Center. He specializes in agentic AI and LLMs, computer vision for optical music recognition, and multilingual text-to-speech systems, combining hands-on model development with MLOps and API engineering. Gianluca has contributed to TensorFlow Probability—implementing and testing a TriResNet bijector—demonstrating practical experience in probabilistic modeling and open-source collaboration. His toolkit spans LangChain, Hugging Face, Watsonx, FastAPI, and containerized environments (Poetry, Docker, Conda), enabling end-to-end production workflows. Based in Apulia, Italy, he also applies his technical skills to social impact projects, having led technological and logistical innovation for a volunteer organization serving over 100 families. He is currently focused on autonomous orchestration of AI agents, blending research depth with production-grade engineering.
8 years of coding experience
Engineering/Industrial Management, Engineering/Industrial Management at Università LUM
Probabilistic reasoning and statistical analysis in TensorFlow
Role in this project:
ML Engineer / Data Scientist
Contributions:6 reviews, 111 commits, 8 PRs in 10 months
Contributions summary:Gianluca primarily worked on implementing and refactoring a `TriResNet` bijector within the TensorFlow Probability library, focusing on its application to probabilistic reasoning and statistical analysis. Their contributions involved initial implementations, code refactoring, and variable definitions. Further, they added tests related to the implemented bijector.
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.