Naav Ai

Position Summary We are seeking an AI Engineer to lead the development of an agentic AI platform for audio content. This role involves architecting, training, and deploying intelligent agents that can autonomously handle audio content production, personalisation, and interactive experiences. You'll be responsible for building context engines, implementing custom agent frameworks using LangChain and LangGraph, and integrating STT/TTS systems with LLMs to create seamless voice-first AI experiences. Key Responsibilities Design intelligent agents for audio content creation and personalization. Develop multi-agent workflows for collaborative audio production. Implement Speech-to-Text (STT) for transcription and voice commands. Build advanced Text-to-Speech (TTS) with natural, emotional voices. Create custom voice cloning models for consistent narration. Design real-time audio processing pipelines. Fine-tune LLMs for summarisation, analysis, and narrative tasks. Develop content recommendations and personalisation features. Build conversational agents for interactive audio content experiences. Enable voice-controlled navigation and bookmarking. Design adaptive narration that learns user preferences. Implement Django/PostgreSQL backends for audio operations. Develop scalable APIs for audio streaming and processing. Create context engines that remember user interactions. Build dynamic systems that adapt to engagement and feedback. Technical Expertise: Degree in Computer Science, AI/ML, or related field (focus on speech/NLP preferred). Overall experience: 3-5 years, with at least 2+ years hands-on with speech tech (STT/TTS), LLMs, or agent frameworks. Strong experience with LangChain/LangGraph for agent-based applications. Proficiency in Python (Django) for backend development. Hands-on experience with PostgreSQL design and optimisation. Expertise in STT systems (Whisper, Google, AWS, etc.). Strong skills in TTS technologies (ElevenLabs, Azure Speech, Google TTS, etc.). Solid understanding of LLMs (fine-tuning, prompt engineering, deployment). Experience with audio processing libraries (librosa, pydub, ffmpeg). Specialized Skills: Knowledge of voice cloning and neural speech synthesis. Experience with audio quality assessment and enhancement techniques. Familiarity with conversational AI and dialogue systems. Experience with vector databases and embeddings for content similarity. Understanding of real-time audio streaming and WebRTC. Knowledge of microservices/event-driven architectures. Experience with model monitoring, evaluation, and A/B testing for audio quality. Bonus (Nice to Have): Understanding of phonetics, prosody, and speech synthesis. Knowledge of multi-language, accents, and accessibility in audio. Experience with speaker identification, conversion, and audio standards. Preferred Qualifications Experience with audio content or podcast platform development Knowledge of publishing industry standards and metadata formats Background in content recommendation systems Experience with real-time audio processing and low-latency systems Familiarity with voice UI/UX design principles Knowledge of copyright and content licensing in digital media Application Process - Please submit: 1. Resume highlighting relevant AI/ML, speech technology, and backend development experience 2. Portfolio showcasing projects involving: LangChain/LangGraph implementations STT/TTS system integration Django applications with audio processing LLM fine-tuning or deployment 3. Brief cover letter explaining your passion for audio technology and AI 4. Links to relevant GitHub repositories or demos featuring: Voice AI applications Audio processing projects Conversational AI systems Python/Django implementations Send your application to: careers@naavai.com