Voice LLM / Conversational AI Engineer

About the Role We are hiring a Voice LLM / Conversational AI Engineer to build real-time voice-first AI agents using LLMs, ASR, TTS, and conversational pipelines. The ideal candidate has hands-on experience building production-grade conversational AI systems, not just demos. You should understand how to create natural multi-turn conversations, handle interruptions, manage context, reduce latency, and deploy reliable voice AI products. ## Key Responsibilities - Build real-time voice conversational agents using LLMs, ASR, and TTS. - Design multi-turn dialogue flows, memory, fallback logic, and context handling. - Optimize latency across speech-to-text, LLM response generation, and text-to-speech. - Work with streaming audio, WebSockets, WebRTC, or telephony systems. - Integrate LLMs with tools, APIs, databases, and workflows. - Evaluate and improve conversation quality, accuracy, reliability, and task completion. - Deploy, monitor, and improve AI systems in production. ## Requirements - 3+ years of experience in AI/ML, NLP, speech AI, or conversational AI. - Hands-on experience with LLMs and voice-based AI systems. - Strong Python skills. - Experience with ASR/TTS tools such as Whisper, Deepgram, ElevenLabs, Azure Speech, Google Speech, or similar. - Understanding of prompt engineering, RAG, agents, memory, and function calling. - Experience building APIs and backend systems. - Strong understanding of latency, streaming, and real-time conversation design. ## Preferred Qualifications - Experience with WebRTC, SIP, Twilio, Exotel, Plivo, or similar platforms. - Experience with multilingual voice AI, especially Hindi, Hinglish, or Indian languages. - Experience with fine-tuning, embeddings, vector databases, or open-source LLMs. - Experience deploying models using Docker, Kubernetes, AWS, GCP, or Azure. - Prior startup experience. ## About the Role We are hiring a Voice LLM / Conversational AI Engineer to build real-time voice-first AI agents using LLMs, ASR, TTS, and conversational pipelines. The ideal candidate has hands-on experience building production-grade conversational AI systems, not just demos. You should understand how to create natural multi-turn conversations, handle interruptions, manage context, reduce latency, and deploy reliable voice AI products. ## Key Responsibilities - Build real-time voice conversational agents using LLMs, ASR, and TTS. - Design multi-turn dialogue flows, memory, fallback logic, and context handling. - Optimize latency across speech-to-text, LLM response generation, and text-to-speech. - Work with streaming audio, WebSockets, WebRTC, or telephony systems. - Integrate LLMs with tools, APIs, databases, and workflows. - Evaluate and improve conversation quality, accuracy, reliability, and task completion. - Deploy, monitor, and improve AI systems in production. ## Requirements - 3+ years of experience in AI/ML, NLP, speech AI, or conversational AI. - Hands-on experience with LLMs and voice-based AI systems. - Strong Python skills. - Experience with ASR/TTS tools such as Whisper, Deepgram, ElevenLabs, Azure Speech, Google Speech, or similar. - Understanding of prompt engineering, RAG, agents, memory, and function calling. - Experience building APIs and backend systems. - Strong understanding of latency, streaming, and real-time conversation design. ## Preferred Qualifications - Experience with WebRTC, SIP, Twilio, Exotel, Plivo, or similar platforms. - Experience with multilingual voice AI, especially Hindi, Hinglish, or Indian languages. - Experience with fine-tuning, embeddings, vector databases, or open-source LLMs. - Experience deploying models using Docker, Kubernetes, AWS, GCP, or Azure. - Prior startup experience.