Senior ML Engineer - Core Evaluations (Remote)

Bazeta; United States; Remote; USD 180,000 - 240,000; Full time

Benefits offered by this job

Medical, dental, and vision insurance

401(k) retirement savings plan

Equity

42 days of paid time off (PTO, sick, &

Floating holidays & parental leave

Lifestyle spending account – $500/月

Complimentary lunch and snacks

One Medical membership

Job summary

Cantina Labs is seeking a Senior Machine Learning Engineer to lead audio model evaluation, building pipelines for speech generation/recognition and automated dashboards. You will help grow the evaluation team and collaborate with model, data, and product teams to improve performance.

The role emphasizes designing metrics, conducting user studies on Mechanical Turk, and training ASR/TTS models in a fast-paced, remote environment in the United States.

Qualifications

• Strong metrics design to capture model performance.
• Experience designing user studies on Mechanical Turk or similar.
• Experience training and fine-tuning models for evaluation.
• Strong statistical knowledge for comparing evaluation results.
• Excellent engineering and programming skills.
• Experience training ASR/TTS models.
• Experience in ML teams handling very large datasets.

Responsibilities

• Design evaluation pipelines for models in development and production.
• Design user studies for subjective model evaluations.
• Convert requirements into measurable metrics.
• Develop automated evaluation dashboards to compare results.
• Lead and grow the evaluation team as a founding member.
• Collaborate with model, data, and product teams to drive improvements.

Skills

Metrics design

User studies (MTurk)

Model training

Statistics & evaluation

Engineering & programming

ASR/TTS training

Large-scale ML (>3B models)

Tools

Mechanical Turk

Job description

Cantina Labs is seeking a Senior Machine Learning Engineer to lead audio model evaluation, building pipelines for speech generation/recognition and automated dashboards. You will help grow the evaluation team and collaborate with model, data, and product teams to improve performance.

The role emphasizes designing metrics, conducting user studies on Mechanical Turk, and training ASR/TTS models in a fast-paced, remote environment in the United States.