Voice AI Engineer

Role overview Build voice experiences that let people speak naturally with AI agents across browser and phone channels. The work spans speech recognition, spoken responses, and conversation handling, with a focus on reducing delays and making interactions resilient to interruptions, corrections, silence, and unclear speech.

Responsibilities - Create agent voice interfaces using speech-to-text and text-to-speech services. - Handle interruptions, corrected details, pauses, and ambiguous speech in conversation flows. - Measure response time and improve latency. - Test voice interactions against realistic customer scenarios. - Work with product colleagues on voice experiences for web and phone.

Requirements - Experience building real-time audio or voice applications. - Working knowledge of speech recognition and synthesis APIs, plus WebRTC or WebSockets. - Strong skills in TypeScript, JavaScript, or Python. - Attention to conversational quality and a habit of measuring it. - Relevant experience may include voice assistants, IVR, real-time communications, conversational AI, or audio engineering with web development.

Benefits and work setup Remote contract with flexible hours. Compensation starts at $5,500 per month. Freelancers and solo agencies may continue working with their own clients. The selection exercise is to build a booking agent for three services, add browser-based speech recognition and spoken replies, test normal and difficult exchanges, measure latency, and demonstrate one improvement. There is no time limit.