Matias Martinez, PhD in Computer Sciences

Personal Sites:
Hello, I am Matias, researcher on AI-based software engineering at the Universitat Politecnica de Catalunya (Barcelona, Spain).
Current Interests and News:
Automated Software Development & Testing
– I have developed tools and approaches to automate the development, evolution, and maintenance of software systems, with a strong focus on data-driven and AI-based approaches. Target tasks include Fault Localisation, Bug and Issue Repair/Fixing, Software Migration and Code Translation.
AI and Machine Learning:
– Recently surveyed Agent-based approaches for issue resolving from SWE-Bench ArXiv draft version.
– Special interests on Large Language Models (LLM) for code tasks, specially on those that are open-source. For instance, recently published work on Sustainability of LLMs for code repair ACM TOSEM 2025.
– Research record on AI-based Software Engineering and Software Testing. Check my Google Scolar profile.
– Latest Hackathon Projects: During 2024, I participated in HACKBCN AI edition where our project won the award “Best developer solution” and in AINAHACK where I developed a solution using BSC’s Salamandra LLMs.
Transferring Knowledge and Technology to Practice:
– Interested in automating the development and maintenance processes in your company? Let’s talk Email.
About teaching:
– I am a teacher in a Master course on MLOps at the Universitat Politecnica de Catalunya (Barcelona, Spain). I teach how to build, test and deploy AI-based systems.
Experience
Universitat Politécnica de Catalunya (UPC), Spain
January 2023-Present
Researcher in AI-based Software Engineering
KTH, Sweden
Jan 2021- Dec. 2022
Researcher in AI-based Software Engineering
University of Polytechnique Hauts-de-France and CNRS, France
Sept. 2016 - 2022
Associate professor
Inria & Univ. of Lille, France
Oct. 2011 - Oct. 2014
PhD student
Baufest, Argentina.
March 2009 - Sept. 2011
Software Engineer, Java & Web developer, architecture consultant
EDSA, Argentina
Sept. 2006 - Dec. 2007
Java developer
Education
PhD in Computer Science
Université de Lille (France)
Software and System Engineering
Universidad del Centro de la Prov Buenos Aires -UNICEN-(Argentina)
Competitions
HACKBCN AI edition (Barcelona)
2024
Best developer solution
Ranking of Most Impactful Early-stage Software Engineering Researchers
2013-2020
Second place (worldwide)
Ranking of Most Active Early-stage Software Engineering Researchers in Top-Quality journals
2013-2020
Nineteenth place (worldwide)
Tools & technologies
RAG (LlamaIndex, LangChain)
ML tools (PyTorch, Pandas, HuggingFace libraries)
CI/CD (Github Actions, Jenkins, Travis)
Deployment (Docker)
Services (Spring Boot -Java-, FastAPI, Django -Python-)
LLM inference (vLLM, HuggingFace accelerate)
Energy and Resource measurement of AI system (Nvidia-smi, IntelRAPL)
Skills
- Agile methodology
- Scrum Master certification
- Java & Python programming
- Software Architecture
- Software testing
- Continuos integration & deployment
- Databases (Relational, Non-relational, Vector)
- Green AI and Software sustainability
Open-source tools developed
- Designed and built from scratch by me:
- github.com/SpoonLabs/Astor
- github.com/SpoonLabs/coming
- github.com/SpoonLabs/gumtree-spoon-ast-diff/
- github.com/ASSERT-KTH/flacoco
- Contributor (and author of the scientific article)
- https://github.com/GumTreeDiff/gumtree
Research topics:
- Automated Software Engineering: – Neural Network and Search based automated program repair – Correctness of generated code – Agentic repair systems
- Green/Sustainable Computing – Energy consumption during training and inference of AI
- Software evolution:
– Structural Differencing of code – Evolution patters and trends – Software migration (e.g., Java to Kotlin)