19 days ago
Remote, United StatesMid Level / Senior
H1B Sponsor
Base Salary
$200k - $220k/yr
Responsibilities
- Design, train, and improve audio VAEs, neural codecs, and vocoders.
- Architect and implement diffusion and flow-matching transformers for audio and video generation.
- Design audio conditioning and cross-modal alignment for joint AV models.
- Run and analyze scientific experiments to enhance model understanding.
- Define data requirements and collaborate on data acquisition and quality filtering.
- Design evaluations for audio fidelity, intelligibility, and AV-sync.
- Optimize inference efficiency to meet latency and cost targets.
- Harden the training, evaluation, and inference pipeline.
- Partner with infrastructure for distributed training and inference.
- Lead small research projects and collaborate on larger initiatives.
- Develop tools to enhance team productivity.
- Contribute to safety and responsibility measures for AI technology.
Requirements
- Exceptional experience with large-scale audio models over 8B parameters.
- Hands-on experience with diffusion and flow-matching transformers.
- Experience training audio VAEs, neural audio codecs, and vocoders.
- Strong experience with multi-node, multi-GPU distributed training.
- Proven software engineering skills in building complex systems.
- Proficiency in PyTorch and performance optimization.
- Experience shipping large-scale speech/audio or multimodal generative models.
- Background in large-scale ML data management.
- Experience with voice cloning and expressive speech generation.
- Notable publications or open-source contributions in relevant fields.
- Preferred experience with multimodal audio-video modeling and video generation.
Benefits
- Competitive salary and generous company equity.
- Medical, dental, and vision insurance with 99.99% premiums covered.
- 42 days of paid time off, including PTO, sick days, and holidays.
- Generous parental leave and fertility support.
- 401(k) retirement savings plan.
- Lifestyle spending account of $500/month.
- Complimentary lunch and snacks for in-office employees.
- One Medical membership.
Categories
About Cantina
Cantina Labs is a social AI company, developing a suite of advanced real-time models that push the boundaries of expression, personality, and realism. We bring characters to life, transforming how people tell stories, connect, and create. We build and power ecosystems. Cantina, our flagship social AI platform, is just the beginning.