About the role
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 TTS and adjacent tasks (voice cloning, controllable TTS, voice conversion 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. 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. Project Leadership: Independently lead small research projects while collaborating on larger team initiatives. 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. GPU Scaling: Partner with infrastructure to run distributed training/inference on cloud fleets and productionize models with reliability and observability. 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 (>3B models and >500k hours data). Exceptional understanding and hands-on experience with transformer architectures and/or diffusion models (inc. distillation and streaming) and/or audio language modelling. Strong experience with multi-node and multi-gpu distributed model training. 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 models to production. Background in working with large-scale ML data. Ability to iterate on data,, and triangulate quality using subjective and objective signals. Notable publications and/or open source contributions in speech/audio/ML. Experience with voice-cloning, speech-control, voice-generation. Preferred Experience: Shipped large scale speech/audio models (TTS/VC/ASR) to production. Work on large-scale ML systems. Experience with audio language modelling, transformer architectures. Experience with voice-cloning, speech-control, voice-generation. Background in processing large-scale ML data. Publications or notable open-source in speech/audio/ML.