Conversational AI Engineer

About the role Build and deploy production-ready conversational AI applications, including chatbots, assistants, and AI agents. This full-time role spans large language models (LLMs), retrieval systems, backend services, and speech technologies to deliver scalable, real-time experiences. Key responsibilities - Design, build, and deploy LLM-powered conversational applications. - Develop backend services and APIs using Python with FastAPI or Flask. - Build retrieval-augmented generation (RAG) pipelines using embeddings, vector databases, and retrieval systems. - Integrate Speech-to-Text (STT) and Text-to-Speech (TTS) technologies. - Design conversation memory, context management, and session-handling systems. - Enable real-time AI interactions through WebSockets or streaming APIs. - Monitor, evaluate, and improve AI systems using prompt management and observability tools. - Ensure application reliability, scalability, and production readiness. Requirements - Hands-on experience building LLM-based conversational AI systems. - Strong Python proficiency and experience with FastAPI or Flask. - Experience integrating STT and TTS services such as Deepgram, ElevenLabs, or similar tools. - Understanding of RAG pipelines, embeddings, and vector search. - Knowledge of conversational memory, context, and session management. - Preferred: familiarity with SIP, RTP, VoIP, or WebRTC. - Preferred: experience with LLM observability tools such as Langfuse, Phoenix, or similar tools. - Preferred: experience building real-time systems using WebSockets (WSS).