AI Voice Agent Engineer
Join a forward-thinking AI team focused on building intelligent voice agents that can communicate naturally with people over the phone.
In this role, you’ll combine conversational AI, natural language processing, speech recognition, and voice synthesis technologies to create responsive, human-like voice experiences for a variety of real-world applications.
You’ll work across the full voice AI pipeline, from understanding what callers are saying to determining the appropriate response and delivering it naturally in real time.
Responsibilities
Design, develop, and improve AI-powered voice agents for different industries and use cases.
Build natural language understanding systems capable of recognizing user intent, extracting relevant information, and maintaining context throughout conversations.
Develop intelligent dialogue management and context-aware conversation flows that enable voice agents to handle complex, multi-step interactions.
Integrate voice applications with telephony platforms and services such as Twilio and Vonage.
Build and optimize real-time speech-to-text and text-to-speech pipelines for smooth, low-latency conversations.
Train, fine-tune, and customize conversational models for specific business domains and customer requirements.
Monitor voice agent performance, analyze conversation data, identify weaknesses, and continuously improve response accuracy and interaction quality.
Work directly with clients and internal teams to customize conversation styles, workflows, and voice personalities for different applications.
Requirements
At least 3 years of professional experience working with conversational AI, voice technology, or related AI systems.
Strong Python programming skills and experience developing production-ready AI applications.
Hands-on experience with NLP technologies and frameworks such as Hugging Face, spaCy, or comparable tools.
Understanding of speech processing technologies and real-time communication protocols, including SIP and WebRTC.
Experience working with AI and cloud platforms such as OpenAI, Google Cloud AI, AWS, or similar services.
Solid knowledge of intent recognition, dialogue management, conversation design, and contextual language processing.
Familiarity with modern speech synthesis and text-to-speech technologies.
Strong analytical, debugging, and problem-solving abilities, particularly when working with complex AI systems.
Nice to Have
Previous experience integrating Twilio, Vonage, or similar communications APIs.
Familiarity with LangChain or other frameworks used to build LLM-powered applications and agents.
A background or practical knowledge in linguistics, speech science, or conversational design.
Experience developing multilingual voice applications, particularly those supporting languages such as Arabic, Hindi, or Urdu.