Vrindavan Harrison (Davan) is a PhD-trained NLP researcher and engineer with 11 years of applied experience building and evaluating dialogue systems and controllable natural language generation. He recently defended a dissertation at UC Santa Cruz on over-generate-and-rank methods to jointly control stylistic variation and semantic accuracy, producing practical artifacts like a LoRA-adapted Llama-3.2-3B slot-error evaluator and a prompt-based stylistic control framework for GPT-4o/Llama-2. He led Team Athena in four Alexa Prize challenges, shipping a production socialbot that handled hundreds of concurrent Alexa users and validated a transformer response ranker via live A/B tests. His work bridges research and production—16+ peer-reviewed papers, internships at Amazon Alexa AI and Microsoft, and deployable models for multilingual transliteration and retrieval-augmented LM adaptation. Based in the SF Bay Area, he’s seeking applied scientist or research roles focused on LLM evaluation, controllable gen, dialogue, or AI alignment.
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.
Request Free Trial
Vrindavan Harrison - Graduate Research And Teaching Assistant