💼 About This Role

You'll architect novel large-scale models for audio understanding tasks and deploy them to production. Your work will go beyond traditional speech recognition to encompass full-spectrum audio perception. You'll set new standards for evaluating audio understanding systems.

🎯 What You'll Do

• Architect and develop novel large-scale models for audio understanding
• Pioneer research in self-supervised learning for audio
• Set new standards for evaluating audio understanding systems
• Build large-scale pre-training and fine-tuning datasets

📋 Requirements

• Deep expertise in ASR or audio understanding
• Experience with large-scale training and GPU/TPU acceleration
• Strong applied mindset balancing scientific novelty with product impact

✨ Nice to Have

• Experience in self-supervised learning for audio
• Experience in few-shot learning
• Experience in robust audio-visual perception

🎁 Benefits & Perks

• 🍽 Lunch, dinner and snacks at the office
• 🏥 Fully covered medical, dental, and vision insurance for employees
• 🏦 401(k)
• ✈️ Relocation and immigration support