Voice Conversion ML Engineer — Equity & PTO Included

Bazeta; Idaho; Hybrid; USD 180,000 - 240,000; Full time

Benefits offered by this job

Medical, dental, and vision insurance

401(k) retirement savings plan

Generous PTO and holidays

Job summary

Cantina is hiring a Machine Learning Engineer to join the Speech Team. You will architect, pre-train, fine-tune, and align large-scale speech models, exploring controllable TTS and voice design. Collaborate with research, data, and infra to ship reliable, cost-aware systems.

You will design experiments, build tools, and contribute across the stack from data requirements to production inference, while maintaining safety and guardrails for responsible speech tech.

Qualifications

• Expertise in large-scale audio models (>8B parameters) and >500k hours of data.
• Experience with diffusion or flow-matching transformers and vocoder design.
• Strong distributed training across multi-node, multi-GPU environments.

Responsibilities

• Architect and train large-scale speech models end-to-end.
• Design experiments and evaluate with objective/subjective measures.
• Develop dev tooling to boost team productivity.

Skills

PyTorch

Distributed training

Speech models

Audio codecs

Model evaluation

Education

MS/PhD in ML

Tools

DeepSpeed

CUDA

Triton

C++

Job description

Cantina is hiring a Machine Learning Engineer to join the Speech Team. You will architect, pre-train, fine-tune, and align large-scale speech models, exploring controllable TTS and voice design. Collaborate with research, data, and infra to ship reliable, cost-aware systems.

You will design experiments, build tools, and contribute across the stack from data requirements to production inference, while maintaining safety and guardrails for responsible speech tech.