AI Voice Agent Engineer

CAIL.IO (Headquarters: Remote)

LLM TTS STT AI Voice AI VoIP Python NLP Startup Conversational AI Speech Recognition Backend AI Engineer

CAIL.IO is building an AI-powered phone operator designed to transform phone calls into effortless experiences, reducing anxiety and saving time for users. Our voice agents, powered by Large Language Models (LLMs), make calls, handle hold music, ask necessary questions, and provide concise summaries. We integrate LLMs, VoIP, and calendar functionalities to create a seamless service with real-world impact. We are a small, remote, pre-seed startup offering significant ownership and the chance to shape a groundbreaking product.

We are seeking experienced AI Voice Agent Engineers to join our core team.

Responsibilities:
* Design, develop, implement, and refine the core AI voice agent capabilities.
* Work extensively with LLMs for natural language understanding, generation, and conversation flow management.
* Integrate, evaluate, and fine-tune Text-to-Speech (TTS) and Speech-to-Text (STT) systems for optimal performance and natural interaction.
* Architect and build robust backend systems leveraging VoIP technologies.
* Contribute to the overall system design and technical strategy.
* Collaborate closely with the team to tackle challenging problems in conversational AI, voice synthesis, and speech recognition in real-world scenarios.
* Ensure the reliability, scalability, and quality of the voice AI platform.

Technical Skills Required:
* Proven experience with Large Language Models (LLMs) in practical applications.
* Hands-on experience with Text-to-Speech (TTS) and/or Speech-to-Text (STT) technologies and frameworks.
* Strong programming skills (e.g., Python).
* Familiarity with cloud platforms and distributed systems.
* Experience with VoIP technologies is a plus.
* Understanding of machine learning principles and pipelines.

Ideal Candidate:
We are looking for someone passionate about AI and voice technology with practical experience building or integrating sophisticated AI voice systems. You should be comfortable working in a fast-paced, early-stage startup environment, capable of taking ownership, dealing with ambiguity, and driven to build technology that directly helps users.