PyTorch/CUDA Expert for Audio AI Pipeline

Job Description: I'm running a self-hosted, real-time conversational voice AI pipeline (STT → LLM → streaming TTS over WebSocket) on a RunPod GPU pod (CSM-1B TTS model, using the davidbrowne17/csm-streaming fork with Sesame's Mimi/moshi audio codec, PyTorch torch.compile)... (Budget: ₹1500 - ₹12500 INR, Jobs: Audio Processing, Audio Services, CUDA, Python)