Looking fro an engineer to build real-time voice and video agents using advanced machine learning models, integrating speech recognition, natural language understanding, and text-to-speech systems. Your work will also involve facial animation and avatar rendering, with a focus on performance and real-time responsiveness. 
Essential Skills-

Strong experience with speech technologies (e.g., Whisper, DeepSpeech, Tacotron, VITS, etc.).
Familiarity with video synthesis and avatar animation (e.g., DeepMotion, NVIDIA Omniverse, D-ID, or similar).
Proficiency in Python and ML frameworks (e.g., PyTorch, TensorFlow).
Experience with real-time systems, streaming protocols, and GPU acceleration.
A creative mindset and passion for building human-centric AI.Desirables-

Experience with LLMs and conversational AI frameworks (e.g., Rasa, LangChain).
Knowledge of emotion detection, prosody modeling, or affective computing.
Familiarity with Unity, Unreal Engine, or WebGL for avatar rendering