▶ Watch ↗AI Engineer World's Fair 20241:57:58
Conference affiliation: Microsoft · 2024
Miguel Martinez is a principal AI solution engineer at Microsoft whose career spans healthcare data science and helping businesses develop AI applications. His work connects company data with model capabilities: retrieving product information and customer purchase histories for retail assistants, integrating agents with external software, and teaching developers to use multimodal models.
Originally from Venezuela, Miguel moved to the United States with his family during high school. He spent seven years at UnitedHealth Group, becoming a principal data scientist at Optum, where his work included pharmacy operations and hospital admissions. He then joined Microsoft as a senior technical specialist for data and AI, before becoming a principal AI solution engineer.
At Microsoft, Miguel helps customers develop applications for their businesses. In his introduction to a 2024 retail copilot workshop, he described working with startups and other businesses that knew about OpenAI and ChatGPT but needed help deciding how to apply them.
David Smith and Cedric Vidal led the workshop, with Miguel assisting participants through the hands-on work. The application combined product information retrieved through Azure AI Search with customer purchase histories stored in Azure Cosmos DB. Those two sources gave the model different kinds of context: what the retailer sold and what the customer had already bought. Miguel’s role was to help participants work through the implementation, rather than to present the architecture as his individual contribution.
Miguel’s instruction also covers ways to extend an assistant beyond text generation:
▶ Watch ↗AI Engineer World's Fair 20241:57:58
Loading more talks and highlights…