Real-Time Multimodal AI Architect - Vision & Audio

Hyphen Connect Limited is looking for a talented Multimodal AI Systems Architect in Singapore. This role focuses on developing and optimizing AI systems that seamlessly integrate vision and audio models, enhancing capabilities in voice-to-voice interactions.

You will integrate vision encoders and audio-native models, optimize streaming latency, and architect multimodal systems for retrieving insights from various media. Candidates should have experience with Whisper, CLIP, and cross-modal alignment.