< session />
Building Multimodal Apps with Gemini 2.0 and Gemini SDK
Wed, 23 April
This hands-on workshop introduces Gemini 2.0 and the Gemini SDK. Participants will explore Gemini's capabilities and its enhanced reasoning ("Thinking") capabilities, including multimodal input processing, and code generation. Through practical exercises, attendees will learn to leverage the Gemini SDK to rapidly develop applications that utilize Gemini models from Google AI or Google Cloud.
Note: This workshop will be offered on both Wednesday, 23 April and Friday, 25 April. If you miss one session, you can catch the other!
Target Audience
- AI/ML Developers – Exploring cutting-edge foundation models for intelligent application development.
- Full-Stack & Front-End Developers – Looking to add powerful AI features via SDKs and APIs.
- Cloud Architects – Integrating Google AI capabilities into scalable cloud-native environments.
- Innovation & Product Teams – Building next-gen multimodal user experiences with minimal overhead.
< speaker_info />
About the speaker
Anchit Nishant
AI Specialist, Google Cloud
Anchit is an AI Specialist at Google Cloud, with expertise in technologies like Gemini, Vertex AI, and the development of advanced RAG systems. He architects and delivers multiple cutting-edge AI solutions, helping businesses to solve complex challenges and achieve breakthrough results. His deep expertise spans solution architecture, cloud computing and transformations, enabling him to guide organizations through every stage of their journey.
Vikas Mishra
AI and Platform Architect, Google Cloud
Vikas is an AI and Platform Architect at Google Cloud, where he designs and implements cutting-edge solutions for APAC's largest consumer and internet companies. He specializes in leveraging AI/ML, cloud-native architectures, and high-performance computing to help businesses scale and overcome complex technical challenges.
