Remote Machine Learning Engineer - Voice Conversion

Description:

• Join Cantina's Speech Team as a Research / ML Engineer to build advanced speech systems end-to-end.
• Collaborate with research, data, and infrastructure to develop reliable and cost-effective models for voice conversion and related tasks.

Requirements:

• Experience with large-scale audio models (>8B parameters, >500k hours of data).
• Proficient in diffusion/flow-matching transformers, audio VAEs, neural audio codecs, and vocoders.
• Strong software engineering skills, particularly in PyTorch and performance optimization.
• Experience with multi-node, multi-GPU distributed training and shipping large-scale speech/audio models to production.
• Background in voice cloning, speech control, or expressive speech generation.
• Notable publications or open-source contributions in speech/audio/ML.

Benefits:

• Competitive salary ($200,000-$220,000) and generous company equity.
• Comprehensive medical, dental, and vision insurance (99.99% premiums covered).
• 42 days of paid time off, including PTO, sick days, and holidays.
• Generous parental leave, fertility support, and a 401(k) retirement plan.
• $500/month lifestyle spending account and complimentary in-office meals.