Description

You will build LLM-powered conversational AI systems, including speech-enabled interactions and real-time streaming pipelines.

This role is hybrid.

Responsibilities

• Develop speech-enabled interactions using STT and TTS technologies.
• Integrate avatar-based real-time lip-sync and animation features.
• Design and maintain real-time AI pipelines and streaming systems.
• Build RAG pipelines and knowledge-integrated chat systems.
• Deploy scalable applications using Docker and cloud platforms.

Required Skills

• 5+ years of experience with Python.
• Expertise in NLP, Generative AI, and Conversational AI.
• Hands-on experience with LLMs (OpenAI, Azure OpenAI, Claude).
• Proficiency with LangChain, LlamaIndex, and RAG pipelines.
• Knowledge of Vector Databases such as Pinecone, FAISS, or Weaviate.
• Experience with FastAPI, Flask, and API development.
• Familiarity with AWS, Azure, or GCP.

Preferred Skills

• Experience with speech-to-text and text-to-speech systems.
• Background in real-time audio/video processing.

Key Skills

Education

Any Graduate