At Google, I’ve worked across Search Quality and Trust & Safety, measuring abuse and quality in web, multimodal, and conversational search. Most recently, I led detection and evaluation of new abuse trends across GenAI Search surfaces, including AI Mode and AI Overviews.
In Google’s Webspam team, I identified behavioral signals that powered automated filtering deployments and reduced spam by ~90% in one year. I also built evaluation frameworks and ground-truth labels for multilingual LLM detection of borderline content.
Earlier in Webspam, I established quality evaluation frameworks for the Discussions and Forums product launch on Search. I also built SpamBrain monitoring and review workflows, and created curated training sets and feedback loops that increased reviewer recall by 4x.
My Trust & Safety work included election integrity analysis and executive metrics for AdWords policy operations. I’ve also built machine-learning classifiers and chatbots at NCR Corporation and optimized financial and supply-chain processes at Deloitte Consulting.

