AI Voice Engineer

Jobtailor; Los Angeles (CA); On-site; USD 120,000 - 180,000; Full time

Job summary

Jobtailor seeks an experienced software engineer to design and build real-time voice-to-voice AI agents. You will create conversational AI systems with LLMs, integrate Speech-to-Text and Text-to-Speech, and optimize latency for natural conversations.

You will develop backend services in Python and C#/.NET, integrate with telephony and streaming platforms, and implement RAG workflows. Collaboration with product managers and AI engineers is essential.

Qualifications

• Bachelor’s or Master’s in CS/SE/AI or related field.
• 3+ years of professional software engineering experience.
• Hands-on experience building voice-to-voice AI applications.
• Strong understanding of ASR, TTS, VAD, audio streaming, and low-latency communication.
• Professional experience with Python and C#/.NET.
• Experience consuming AI APIs and working with LLMs.
• Experience building REST APIs and microservices.
• Knowledge of asynchronous programming and real-time streaming.
• Strong debugging and problem-solving skills.

Responsibilities

• Design and develop real-time voice-to-voice AI agents.
• Build conversational AI systems using LLMs and agent frameworks.
• Integrate STT and TTS into production apps.
• Optimize latency and streaming performance for natural conversations.
• Develop backend services and APIs using Python and C#/ .NET.
• Integrate with telephony, voice streaming, and communication platforms.
• Implement memory, tool calling, function execution, and RAG workflows.
• Collaborate with product managers and engineers to deliver production AI solutions.
• Evaluate emerging AI models, speech technologies, and voice platforms.
• Monitor, troubleshoot, and improve voice agent performance.

Skills

Python

C#/.NET

LLMs

Speech recognition

Speech synthesis

Realtime streaming

REST APIs

Asynchronous programming

Problem solving

Education

Bachelor's or Master's in CS/Software Engineering/AI

Tools

Docker

Kubernetes

Azure AI/OpenAI or cloud AI services

Job description

• Design and develop real-time voice-to-voice AI agents
• Build conversational AI systems using LLMs and agent frameworks
• Integrate Speech-to-Text (STT) and Text-to-Speech (TTS) technologies into production applications
• Optimize latency and streaming performance for natural conversations
• Develop backend services and APIs using Python and C#/.NET
• Integrate with telephony, voice streaming, and communication platforms
• Implement conversation memory, tool calling, function execution, and retrieval-augmented generation (RAG) workflows
• Collaborate with product managers, AI engineers, and software developers to deliver production-ready AI solutions
• Evaluate emerging AI models, speech technologies, and voice platforms
• Monitor, troubleshoot, and continuously improve voice agent performance and reliability

Requirements

• Bachelor's or Master's degree in Computer Science, Software Engineering, Artificial Intelligence, or a related field
• 3+ years of professional software engineering experience
• Hands-on experience building voice-to-voice AI applications
• Strong understanding of Speech Recognition (ASR), Speech Synthesis (TTS), Voice Activity Detection (VAD), audio streaming, and low-latency communication
• Professional experience with Python and C#/.NET
• Experience consuming AI APIs and working with LLMs
• Experience building REST APIs and microservices
• Knowledge of asynchronous programming, event-driven architectures, and real-time streaming
• Strong debugging, analytical, and problem-solving skills
• Preferred: experience with real-time conversational AI platforms, AI agent frameworks, RAG, vector databases, prompt engineering and evaluation, WebRTC/SIP/RTP/telephony integrations, Azure AI/Azure OpenAI or other cloud AI services, Docker and Kubernetes, CI/CD pipelines, and cloud-native application development

Core Competencies

Demonstrates expertise in designing and developing real-time voice-to-voice AI agents, integrating Speech-to-Text and Text-to-Speech technologies, and optimizing performance for natural conversations. Proficient in backend development using Python and C#/.NET, with a strong understanding of AI models and voice technologies.