RL
Rohan Lopes
Sr Architect
HomeProjectsArchitectural InsightsSkillsExperienceBlogAI AssistantContact

    Revolutionizing Interviews: Real-Time AI Agents Powered by Gemini Live and Livekit

    A Proof-of-Concept demonstrating AI-powered preliminary job interviews in real-time using Google's Gemini Live API and Livekit for natural, conversational interactions.

    AI-Generated Summary

    Developed a proof-of-concept for real-time AI-powered preliminary job interviews, integrating Google's Gemini Live API for natural conversational intelligence and Livekit for real-time audio/video. My contributions as an AI Prototyper/Developer included setting up Livekit, integrating the Gemini Live API for AI voice and intelligence, developing the Python-based Livekit Agent, and building the Next.js frontend to initiate structured, time-bound interviews based on job descriptions.

    Project Demos & Resources
    Explore the project’s code and documentation on GitHub.
    Details

    Revolutionizing Interviews: Real-Time AI Agents Powered by Gemini Live and Livekit

    My Role

    AI Prototyper / Developer

    Problem Solved

    Traditional preliminary interviews can be time-consuming and resource-intensive. This project aims to automate and streamline this process using real-time AI agents.

    Key Contributions

    Integrated Google's RealTime Model Gemini Live API for AI voice and intelligence, set up Livekit for real-time communication, developed the Python-based Livekit Agent, and built the Next.js frontend to initiate interviews.

    Technologies Used

    Google Gemini Live API (RealTime Model)
    Livekit
    Next.js
    React
    Python
    LangChain (implied for agent instructions)