Tutorials
Gopi Krishnan Rajbahadur
Huawei Canada
Tutorial 1: Software Engineering for Foundation Models (SE4FM)
Gopi Krishnan Rajbahadur is a Principal Researcher at Huawei’s Centre for Software Excellence in Canada, where he leads the data and post-training team for the Pangu Foundation Model, advancing its software engineering capabilities. He is also a Research Associate at the Software Engineering and Analysis Lab (SAIL) at Queen’s University, where he leads research on AI supply chain and trustworthy AI agent ecosystems.
His research focuses on software engineering for AI-powered systems, requirements engineering for AIware, and the governance and compliance of AI datasets. He co-leads the AI and Datasets Profile in the ISO/IEC SPDX standard and co-organizes the International Workshop on Requirements Engineering for AI-powered Software (RAISE).
He also co-organizes the AIware Bootcamp series (Toronto, Ottawa, Amsterdam) and regularly shares practical guidance through talks, tutorials, and briefings at venues such as ICSE, FSE, ASE, KDD, and CSER. His work has appeared in premier venues including TSE, TOSEM, EMSE, and top conferences such as ASE, FSE, ICSE, and KDD.
Foundation models are among humanity’s most complex software systems. They are currently engineered through tribal knowledge and ad-hoc processes, despite quarterly release cadences and rapidly expanding model size, context length, and modality. This 90-minute technical briefing presents SE4FM — a disciplined software engineering framing for FMs — organized around four pillars: DataOps (deciding, curating, optimizing, and governing data), ExperimentOps (hypothesis-driven, scaling-law-aware experimentation from small to large, including RLHF/RLAIF/RLVR pipelines), EvalOps (systematic testing, prioritization, and debugging), and FieldOps (releases, monitoring, and compliance). The goal is to give software engineering researchers a unique insider view of how FMs are really built and run at scale, and to surface concrete SE challenges and opportunities where new SE-centric methods, tools, and theory are urgently needed.
Tutorial 2: Agentic Software Engineering: A Roadmap to Software Engineering 3.0
Hao Li is a postdoctoral researcher at Queen’s University’s SAIL and MCIS Labs. His research focuses on Agentic Software Engineering (AgenticSE) and Software Engineering for Artificial Intelligence (SE4AI). He leads the creation of the AIDev dataset and conducts foundational research on coding agents, AI ecosystems, and machine learning software quality.
He serves as co-chair for the AgenticSE workshops at KDD 2026 and ACM CAIS 2026, as well as Mining Challenge co-chair for MSR 2026.
Software Engineering is shifting from AI-assisted development (SE 2.0) to Agentic Software Engineering (SE 3.0), where autonomous AI agents act as collaborators. This technical briefing establishes the foundations of a disciplined SE 3.0 practice. It synthesizes: (1) a large-scale characterization of agent activity in the wild based on the AIDev dataset, (2) an empirical study of 567 Claude Code pull requests across 157 open-source software projects, and (3) the Structured Agentic Software Engineering (SASE) framework that reframes actors, processes, artifacts, and tools. Attendees will leave with evidence-backed mental models, evaluation patterns for agent-authored pull requests, and a practical vocabulary — including agent command environment and agent execution environment — for designing trustworthy human-agent workflows.