Voice AI Specialist - Software Engineer

Responsibilities:

• Build and ship AI-powered voice agents for real-world customer and business workflows.
• Design and develop voice-based conversational experiences from concept to production.
• Integrate and work with Voice AI platforms, LLMs, STT, TTS, and telephony systems.
• Work with technologies such as Retell, Vapi, Sarvam, Bolna, ElevenLabs, Deepgram, or similar Voice AI platforms.
• Build backend services and integrations that enable voice agents to perform real actions such as booking, scheduling, and dispatching.
• Improve voice-agent performance across latency, accuracy, reliability, conversation quality, and cost.
• Design conversation flows, prompts, tool/function calling, context handling, and agent workflows.
• Debug real-world voice interactions and continuously improve agent behaviour based on production usage.
• Work closely with product, design, and engineering teams to translate business workflows into scalable Voice AI solutions.
• Take ownership of features end-to-end, from experimentation and development to deployment and iteration.
• Work directly with ambiguity and move quickly while maintaining reliability and production quality.

Requirements:

• 2-4 years of experience in software engineering, AI engineering, conversational AI, or a related field.
• Hands-on experience building or deploying Voice AI / voice-agent applications.
• Experience working with one or more Voice AI platforms such as Retell, Vapi, Sarvam, Bolna, ElevenLabs, Deepgram, or similar platforms.
• Strong understanding of LLM-based applications and conversational AI workflows.
• Experience with APIs, backend services, integrations, and production software systems.
• Strong programming fundamentals and ability to build, debug, and ship production-quality software.

Required Skills:

• Strong understanding of Voice AI / Conversational AI systems.
• Hands-on experience with voice agents and conversational workflows.
• Familiarity with STT (Speech-to-Text) and TTS (Text-to-Speech) technologies.
• Experience integrating LLMs with voice applications.
• Understanding of prompt engineering, tool/function calling, context management, and agent workflows.
• Experience with telephony, calling workflows, webhooks, APIs, or real-time communication is a strong plus.
• Strong backend/software engineering fundamentals.
• High ownership and ability to work independently in an ambiguous, fast-moving environment.
• Ability to experiment quickly, identify issues from real conversations, and continuously improve the product.
• Curiosity about how real businesses operate and how AI can automate real-world workflows.

Good to Have:

• Experience with Retell, Vapi, Sarvam, Bolna, ElevenLabs, Deepgram or comparable Voice AI platforms.
• Experience building AI voice agents for production use cases.
• Experience with telephony APIs such as Twilio or similar platforms.
• Experience working with real-time audio or streaming systems.
• Experience with WebSockets, SIP, or real-time communication infrastructure.
• Experience optimising voice-agent latency and response quality.
• Experience building AI agents that interact with external tools, APIs, CRMs, scheduling systems, or business workflows.