Asks for

The ad says“Deep hands-on experience training audio VAEs, neural audio codecs, and vocoders latent/tokenizer design, reconstruction and perceptual objectives, adversarial training.”
The ad says“Exceptional research/development experience with large-scale audio models (>8B parameters, >500k hours of data).”
The ad says“Deep hands-on experience training audio VAEs, neural audio codecs, and vocoders latent/tokenizer design, reconstruction and perceptual objectives, adversarial training.”
The ad says“Strong with PyTorch and performance work (profiling, CUDA/Triton/C++ as needed) and writing reliable production-quality code.”
The ad says“Deep hands-on experience with diffusion and/or flow-matching transformers, including practical knowledge of samplers, schedules, conditioning mechanisms, and distillation.”
The ad says“Strong with PyTorch and performance work (profiling, CUDA/Triton/C++ as needed) and writing reliable production-quality code.”
The ad says“Strong experience with multi-node, multi-GPU distributed training (FSDP/DeepSpeed or equivalent).”
The ad says“Deep hands-on experience with diffusion and/or flow-matching transformers, including practical knowledge of samplers, schedules, conditioning mechanisms, and distillation.”
The ad says“Deep hands-on experience with diffusion and/or flow-matching transformers, including practical knowledge of samplers, schedules, conditioning mechanisms, and distillation.”
The ad says“Strong experience with multi-node, multi-GPU distributed training (FSDP/DeepSpeed or equivalent).”
The ad says“Experience with voice cloning, speech control/steerability, or expressive speech generation.”
The ad says“Deep hands-on experience with diffusion and/or flow-matching transformers, including practical knowledge of samplers, schedules, conditioning mechanisms, and distillation.”
The ad says“Strong experience with multi-node, multi-GPU distributed training (FSDP/DeepSpeed or equivalent).”
The ad says“Deep hands-on experience training audio VAEs, neural audio codecs, and vocoders latent/tokenizer design, reconstruction and perceptual objectives, adversarial training.”
The ad says“Strong with PyTorch and performance work (profiling, CUDA/Triton/C++ as needed) and writing reliable production-quality code.”
The ad says“Deep hands-on experience with diffusion and/or flow-matching transformers, including practical knowledge of samplers, schedules, conditioning mechanisms, and distillation.”
The ad says“Deep hands-on experience with diffusion and/or flow-matching transformers, including practical knowledge of samplers, schedules, conditioning mechanisms, and distillation.”
The ad says“Experience with voice cloning, speech control/steerability, or expressive speech generation.”
The ad says“Strong with PyTorch and performance work (profiling, CUDA/Triton/C++ as needed) and writing reliable production-quality code.”
The ad says“Deep hands-on experience training audio VAEs, neural audio codecs, and vocoders latent/tokenizer design, reconstruction and perceptual objectives, adversarial training.”
The ad says“Experience with voice cloning, speech control/steerability, or expressive speech generation.”

About Cantina:

Cantina is a new social platform founded by Sean Parker with the most advanced AI character creator. Our bots are lifelike, social creatures that can interact wherever people are online—across voice, video, and text. Create yourself, imagine someone new, or choose from thousands of characters to share infinitely scalable, personalized content and seamless group chat.

If you’re excited about how AI can shape creativity and social interaction, come help us build what’s next.

About the Role:

We’re looking for a Research / ML Engineer to join our Speech Team to build state-of-the-art speech systems end-to-end—from data specs through production inference. You’ll drive the model ↔ data ↔ eval flywheel for VC and adjacent tasks (controllable TTS, voice design and more), partnering closely with research, data, and infra to ship fast, reliable, and cost-aware models. In this role, you will work at the intersection of cutting-edge research and practical engineering, contributing to the development of safe, steerable, and trustworthy AI systems.

You will thrive in this role if you:

See research and engineering as two sides of the same coin and enjoy owning work end-to-end.
Are results-oriented, flexible, and willing to pick up whatever moves the needle.
Like collaborating closely with infra, data, and product to ship measurable improvements.
Enjoy designing experiments, listening tests, and metrics that correlate with user-perceived quality.
Eager to learn every-day, find and solve unique large-scale problems.

What You’ll Do:

Model Building: Architect, implement, pre-train, fine-tune, and post-train/alignment (e.g., GRPO/DPO) for large-scale speech models.
Experimental Design: Design, run, and analyze scientific experiments to advance our understanding of the models.
Tool Development: Develop and improve dev tooling to enhance team productivity.
Full-Stack Contribution: Contribute to the entire stack, from low-level optimizations to high-level model design.
Data Ownership: Define data requirements and collaborate on acquisition, curation, augmentation, labeling quality, and synthetic data strategies.
Rigorous Evaluation: Design automated objective/subjective evaluations—listening tests, SV/WER/ASR-based metrics, robustness & bias checks, and red-team studies.
Pipeline Delivery: Harden the training → evaluation → inference pipeline; profile latency, memory, and cost; and meet production SLAs with robust monitoring and rollback.
Safety & Responsibility: Contribute to safety/consent guardrails and to misuse/abuse mitigation for responsible speech technology.

What You’ll Bring:

Exceptional research/development experience with large-scale audio models (>8B parameters, >500k hours of data).
Deep hands-on experience with diffusion and/or flow-matching transformers, including practical knowledge of samplers, schedules, conditioning mechanisms, and distillation.
Deep hands-on experience training audio VAEs, neural audio codecs, and vocoders latent/tokenizer design, reconstruction and perceptual objectives, adversarial training.
Strong experience with multi-node, multi-GPU distributed training (FSDP/DeepSpeed or equivalent).
Strong software engineering skills with a proven track record of building complex systems.
Strong with PyTorch and performance work (profiling, CUDA/Triton/C++ as needed) and writing reliable production-quality code.
Shipped large-scale speech/audio or multimodal generative models to production.
Background in working with large-scale ML data, and the ability to iterate on data and triangulate quality using both subjective and objective signals.
Experience with voice cloning, speech control/steerability, or expressive speech generation.
Notable publications and/or open-source contributions in speech/audio/ML.

Compensation:

The anticipated annual base salary range for this role is between $200,000-$220,000 (€170,000-€190,000). When determining compensation, a number of factors will be considered, including skills, experience, job scope, location, and competitive compensation market data.

Benefits for U.S.-based roles:

Competitive salary and generous company equity
Medical, dental, and vision insurance – 99.99% of premiums covered by Cantina
42 days of paid time off, including:
- 15 PTO days
- 10 sick days
- 15 company holidays
- 2 floating holidays
Generous parental leave & fertility support
401(k) retirement savings plan
Lifestyle spending account – $500/month to use however you’d like
Complimentary lunch and snacks for in-office employees
One Medical membership, and more!