Applied Researcher, Audio

The role

You will lead research at the frontier of realtime conversation and human AI interaction. You will contribute to novel architectures, data, and evals for realtime audio to build state-of-the-art models for voice agents.

What you will do

• Architect and develop new architectures for realtime audio understanding, generation, and speech-to-speech models
• Contribute to frontier multimodal and multilingual datasets for pre-training and post-training
• Curate data mixes and develop new methods for synthetic data generation and annotation
• Set new standards for how to evaluate and benchmark audio models

Required qualifications

• Strong applied mindset and ability to balance scientific novelty with product impact
• Ability to work across the stack from infra, to data, to evals, to architecture
• Deep expertise in deep generative modeling
• Experience with large-scale training, GPU/TPU acceleration, and model optimization

Nice to have

• Previous experience in audio understanding
• Previous experience in audio generation
• Previous experience in speech-to-speech
• Previous experience in language modeling

Benefits

• Competitive base salary
• Attractive equity package
• Fully covered medical insurance
• Dental and vision for you and your family
• 9 weeks paternity leave
• 12 weeks maternity leave
• 401(k)
• Monthly commuter stipend
• Flexible PTO
• Daily lunch, dinner and snacks
• Personal Yoshi

Before you apply

• Visa sponsorship is dependent on many factors and success is not guaranteed
• Cartesia participates in E-Verify and will provide Form I-9 information to confirm employment eligibility after hire

About the company

Cartesia aims to architect AI that learns from and interacts with the world like humans do. The founding team includes PhDs from the Stanford AI Lab who invented State Space Models.