Voice Engineer/Developer - Houston, TX

Role: Voice Engineer / Developer

Location: Houston, TX (Onsite)

Contract

Key Responsibilities

• Design and develop IVR call flows for inbound and outbound customer journeys.
• Develop and deploy AI-powered Voice Bots for customer self-service and automated calling.
• Build conversational workflows using ASR, TTS, NLU/LLMs, and dialogue management.
• Develop integrations with REST APIs, webhooks, CRM systems, databases, and enterprise applications.
• Design bot-to-human escalation while passing on the relevant customer and conversation context.
• Troubleshoot SIP/telephony, API, webhook, call-flow, and voice-quality issues.
• Monitor production IVR and voice-bot applications and resolve incidents.
• Analyze call logs, transcripts, and bot performance to improve containment and customer experience.
• Work closely with Product Managers, Solution Architects, QA, Telecom, and AI/ML teams.
• Develop automated test scenarios for IVR and voice-bot journeys.
• Ensure solutions comply with security, privacy, recording, and telecom requirements.

Required Technical Skills

• 8+ years of experience in IVR, telephony, contact-center, or voice application development.
• Hands-on experience with Exotel or comparable platforms such as Twilio, Amazon Connect, Genesys, NICE, Cisco, Five9, or Avaya.
• Strong understanding of IVR, DTMF, PSTN, SIP, RTP, call routing, call recording, and call transfers.
• Experience developing voice bots/conversational AI.
• Practical knowledge of ASR, TTS, NLU, LLMs, prompt engineering, and conversation flows.
• Strong programming skills in Python, Node.js, Java, or similar.
• Experience with REST APIs, JSON, webhooks, databases, and microservices.
• Experience in integrating voice platforms with CRM and backend systems.
• Knowledge of cloud platforms such as AWS, Azure, or Google Cloud Platform.
• Strong debugging, troubleshooting, and production-support skills.

Preferred Skills

• Experience with OpenAI or other LLM-based voice agents.
• Experience with real-time/streaming audio, WebRTC, streaming ASR/TTS, and low-latency voice applications.
• Familiarity with Dialogflow, Amazon Lex, Rasa, Microsoft conversational platforms, or equivalent.