Machine Learning Engineer - Voice Conversion

As a Research/ML Engineer on Cantina's Speech Team, you'll build state-of-the-art speech systems end-to-end, from data specifications through production inference. You'll drive the model, data, and evaluation flywheel for voice conversion and related tasks like controllable TTS and voice design, partnering closely with research, data, and infrastructure teams to ship fast, reliable, and cost-aware models. In this role, you work at the intersection of cutting-edge research and practical engineering, contributing to the development of safe, steerable, and trustworthy AI systems.

What you'll do

• Architect, implement, pre-train, fine-tune, and post-train/align large-scale speech models using techniques like GRPO and DPO
• Design, run, and analyze scientific experiments to advance understanding of the models
• Develop and improve developer tooling to enhance team productivity
• Contribute to the entire stack, from low-level optimizations to high-level model design
• Define data requirements and collaborate on acquisition, curation, augmentation, labeling quality, and synthetic data strategies
• Design automated objective and subjective evaluations, including listening tests, SV/WER/ASR-based metrics, robustness and bias checks, and red-team studies
• Harden the training, evaluation, and inference pipeline; profile latency, memory, and cost; and meet production SLAs with robust monitoring and rollback
• Contribute to safety and consent guardrails and to misuse and abuse mitigation for responsible speech technology

What you bring

• Exceptional research and development experience with large-scale audio models (more than 8B parameters and more than 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, including latent/tokenizer design, reconstruction and perceptual objectives, and adversarial training
• Strong experience with multi-node, multi-GPU distributed training using FSDP, DeepSpeed, or equivalent
• Strong software engineering skills with a proven track record of building complex systems
• Strong proficiency with PyTorch and performance work, including profiling, CUDA, Triton, and C++ as needed, and writing reliable production-quality code
• A track record of shipping large-scale speech, audio, or multimodal generative models to production
• Background working with large-scale ML data and the ability to iterate on data 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, or ML

What we offer

• Annual base salary of $200,000-$220,000 (€170,000-€190,000), with compensation determined based on skills, experience, job scope, location, and competitive market data
• Generous company equity
• Medical, dental, and vision insurance with 99.99% of premiums covered by Cantina
• 42 days of paid time off annually, including 15 PTO days, 10 sick days, 15 company holidays, and 2 floating holidays
• Generous parental leave and fertility support
• 401(k) retirement savings plan
• Lifestyle spending account of $500 per month
• Complimentary lunch and snacks for in-office employees
• One Medical membership

About Cantina

Cantina is a social platform founded by Sean Parker featuring advanced AI character creation. The platform lets you create lifelike, interactive bots that engage across voice, video, and text, enabling infinitely scalable and personalized content sharing.