Massimiliano Pronesti
Doctoral Researcher at IBM
Dublin, Ireland
Summary
🤩
Rockstar🎓
Top SchoolMassimiliano Pronesti is a doctoral researcher at IBM Research Dublin with seven years of experience applying deep learning, NLP, and ML systems to real-world problems. He combines academic rigor with production-focused engineering from roles at Amadeus and hands-on software development early in his career, working across MLOps, back-end systems, and high-performance computing. An active open-source contributor and long-time Linux user, he has extended popular projects such as pandas-ai (adding Azure OpenAI support and robust test suites) and improved vLLM integrations for high-throughput LLM serving. His work sits at the intersection of research and engineering, making LLMs more usable and deployable in enterprise contexts. Based in Dublin, he holds advanced degrees from Politecnico di Torino and EURECOM and brings a practical curiosity for tooling and infrastructure that accelerates model adoption.
7 years of coding experience
2 years of employment as a software developer
Innovation - Decision Making - Industry 4.0, Innovation - Decision Making - Industry 4.0 at Alta Scuola PolitecnicaMaster of Science (Double Degree) Data Science and Engineering, Master of Science (Double Degree) Data Science and Engineering at EURECOMMaster of Science - MS Computer Science Engineering, Master of Science - MS Computer Science Engineering at Politecnico di Torino
English, Spanish, Italian, French
Github Skills (15)
apim10
openai-api10
api10
openai10
python10
langchain10
azure-openai10
llm10
documentation9
testing9
mlops9
dockers7
docker7
ray7
transformer6
Programming languages (10)
Github contributions (5)
sinaptik-ai/pandas-ai
May 2023 - May 2024
Chat with your database or your datalake (SQL, CSV, parquet). PandasAI makes data analysis conversational using LLMs and RAG.
Role in this project:
Back-end Developer
Back-end DeveloperContributions:41 reviews, 42 PRs, 133 comments in 1 year
Contributions summary:Massimiliano primarily contributed to adding support for Azure OpenAI, including features for auto-deduction of deployment capabilities and implementing test suites. They worked on integrating the Azure OpenAI API within the existing codebase. Their commits also involved refactoring code, fixing linting errors, and adding an OpenAI base class. These changes indicate a focus on expanding the LLM capabilities within the project.
aicsvdatadata-analysisdata-science
vllm-project/vllm
Jun 2023 - Feb 2024
A high-throughput and memory-efficient inference and serving engine for LLMs
Role in this project:MLOps Engineer
MLOps EngineerContributions:6 reviews, 5 PRs, 15 comments in 8 months
Contributions summary:Massimiliano's contributions focus on improving the vLLM project's usability and integration with various tools and platforms. They fixed a Ray-related initialization issue, added instructions for integrating with Langchain, and upgraded examples to use the OpenAI V1 API. They also addressed a Langchain-related documentation issue, and incorporated codespell to perform spell checking throughout the codebase.
amdcudagpthpuinference
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.