Remote Machine Learning Engineer, Speech - Joint Audio-Video Modeling

Description:

• Join Cantina Labs as a Research / ML Engineer in the Speech Team to develop advanced speech and audio generation systems focusing on joint audio-video modeling.
• Own the audio side of multimodal generation, including voice cloning, cinematic dialogue, and adjacent speech tasks.

Requirements:

• Exceptional experience with large-scale audio models (>8B parameters, >500k hours of data).
• Deep hands-on experience with diffusion/flow-matching transformers and audio VAEs, neural codecs, and vocoders.
• Strong software engineering skills, particularly in PyTorch, and experience with multi-node, multi-GPU distributed training.
• Background in large-scale ML data and experience with voice cloning or expressive speech generation.

Benefits:

• Competitive salary range of $200,000-$220,000 and generous company equity.
• Comprehensive medical, dental, and vision insurance with 99.99% of premiums covered.
• 42 days of paid time off, including PTO, sick days, and company holidays.
• Additional benefits include generous parental leave, 401(k) plan, lifestyle spending account, and complimentary in-office meals.