Bio

Weiran Yao is a senior research scientist at Salesforce AI Research in Palo Alto. He drove cross-functional initiatives for agentic AI systems for software engineering and multi-agent orchestration, leading teams of 4 scientists/engineer. He can be reached at this Email

At Salesforce, he’s led developed agentic AI systems including Salesforce CodeGenie Agent, DigitalHQ, SEDA, Salesforce Research Ensemble Agents, and Salesforce WebAgent.

For LLM training, he’s led post-training of Retroformer, a general critic model for agent self-reflection. He worked on xLAM, a family of state-of-the-art language models for function calling. He conducted research on synthetic data generation pipeline for APIGen and AgentOhana.

For Engineering Products, He developed automatic root cause analysis algorithms, or SRE/AIOps agent. He worked on function call and structured output API endpoints for Salesforce xLAM services. He did his PhD and MS in Machine Learning at CMU, focused on Model Interpretability, where he was advised by Kun Zhang.