News

• [Mar, 2025] I have being recognized as an outstanding IBMer this year! I have being selected to attend IBM Tech 2025, IBM's premier recognition, education, and development conference for top technical IBMers.
• [Feb, 2025] Our paper API Pack: A Massive Multi-Programming Language Dataset for API Call Generation has been accepted at ICLR 2025! Please check my online presentation [here].
• [Dec, 2024] I will be one of the speakers for 'The Future of Software Engineering Beyond the Hype of AI' panel, to be held as part of ICSE 2025.
• [Nov, 2024] I am happy to share that I have been invited to the Dagstuhl Perspectives Workshop on Creativity, GenAI, and Software Development: A Future Together 2025.
• [May, 2024] I had the pleasure to participate during InnovaTec's academic week at the National Technological Institute of Mexico presenting a talk about Software Engineering in the Age of AI.
• [May, 2022] It was a blast attending Cetys University to present an extended version of my dissertation's work Understanding How Information Flows in and out of Regularly Scheduled Software Maintenance Design Meetings: a Case Study for the CINAP's research seminar.

Research

My research centers on creating high-quality synthetic data to enhance the effectiveness of Granite LLMs and Agent-driven solutions across various domains, with a particular emphasis on software engineering tasks.

Education

My academic journey began in Mexico, where I earned a BSc in Computational Systems Engineering and a Master’s in Engineering. I later obtained a PhD in Software Engineering from the University of California Irvine (UCI) in 2022. During my time at UCI, I was dedicated to supporting talented individuals from Mexico in pursuing research opportunities. In recognition of my contributions, I received the Latino Excellence and Achievement Award in 2021 and was the inaugural recipient of the Rosalva Gallardo Valencia Graduate Award in 2019.

Service

• Organizing Committee Member: CHASE 2024 [short-paper track co-chair], CHASE 2023 [proceedings chair]
• Program Committee Member: ICSE 2026 [Research track], FSE 2025 [Industry track, AI IDE Workshop], ICLR 2025 [Datasets & Benchmarks], ICSE 2025 [Research track (shadow), SE in Practice (SEIP), Artifact Evaluation, Designing Workshop] CHASE 2025 [Research track], ICSE 2024 [Designing Workshop], IEEE Software Special Issues 2024 [Creativity in Software Engineering], CHASE 2023 [Research track], MSR 2021[Research track (shadow)]

Recent Publications

• API Pack: A Massive Multi-Programming Language Dataset for API Call Generation ICLR 2025
• GRANITE 3.0 LANGUAGE MODELS Technical Report
• Power Scheduler: A Batch Size and Token Number Agnostic Learning Rate Scheduler
• Granite-Function Calling Model: Introducing Function Calling Abilities via Multi-task Learning of Granular Tasks EMNLP 2024
• Granite Code Models: A Family of Open Foundation Models for Code Intelligence Technical Report
• Characterizing Software Maintenance Meetings: Information Shared, Discussion Outcomes, and Information Captured ICSE 2024
• Recurring distributed software maintenance meetings: toward an initial understanding CHASE 2022
• KNOCAP: capturing and delivering important design bits in whiteboard design meetings ICSE 2020

For a full list of publications, please check my Google Scholar profile.

Active Research Topics

• AI for Software Engineering: AI for Code, AI Software Agents
• Synthetic Data: Tool/API Instruction Data Generation, Agentic Trajectories Generation, Automatic Instruction Data Selection
• Empirical Studies in Software Engineering: Software Meetings

Languages

• English (fluent)
• Spanish (native speaker)