Join our team and build your career with us
This role focuses on exploring available tools and APIs for real-time speech processing and large language models, designing a low-latency streaming architecture, and implementing a working prototype that enables live voice conversations with an AI system.
– Research and evaluate speech-to-text, text-to-speech, and LLM platforms and tools
– Design and implement a real-time streaming pipeline for voice interaction with LLMs
– Build backend services and APIs to support low-latency, bidirectional communication
– Implement a simple frontend to demonstrate real-time voice interaction
– Document technical findings, architecture decisions, and recommendations
– Design MCP servers and clients for interactivity
