Generative AI Engineer

Yabx is seeking a skilled Generative AI Engineer to join our dynamic team in Gurugram, India. This position focuses on building next-generation AI systems, specifically harnessing the power of Large Language Models (LLMs) and Voice AI. Our primary goal is to develop and deploy production-ready, real-time conversational systems, intelligent AI agents, and sophisticated voice applications.

We are looking for an engineer who thrives on building practical, real-world systems rather than just theoretical models. The ideal candidate will have the ability to design, implement, and deploy LLM-powered applications, voice assistants, and robust real-time AI pipelines. This role offers a unique opportunity to work at the intersection of LLMs, real-time voice technologies, telephony infrastructure, and advanced conversational AI workflows.

Key Responsibilities:

• Develop and deploy LLM-driven applications such as chatbots, virtual assistants, and AI agents.
• Build scalable backend services and APIs using Python, FastAPI, or Flask.
• Implement Retrieval-Augmented Generation (RAG) pipelines, incorporating embeddings, vector search, and retrieval mechanisms.
• Integrate Speech-to-Text (STT) and Text-to-Speech (TTS) technologies into AI applications.
• Design and implement effective memory and context management systems for conversational AI.
• Develop real-time AI interaction systems utilizing WebSockets or streaming APIs.
• Monitor, evaluate, and optimize AI system performance using prompt management and observability tools.

Required Skills:

• Proven experience in building LLM-based conversational AI applications (chatbots, assistants, agents).
• Strong programming skills in Python.
• Proficiency in using FastAPI or Flask for backend service development.
• Experience with integrating Speech-to-Text and Text-to-Speech systems from providers like Deepgram, ElevenLabs, etc.
• Familiarity with RAG pipelines, embeddings, and vector search technologies.
• Solid understanding of conversational AI workflow components, including memory, context, and session handling.

Preferred Skills:

• Knowledge of telephony systems such as SIP, RTP, VoIP, or WebRTC.
• Experience with LLM observability tools like Langfuse or Phoenix.
• Experience working with WebSockets (WSS) for real-time AI system development.