🛠 Tech Stack

💼 About This Role

You'll design and build evaluation pipelines for cutting-edge speech generation and recognition models at a social AI company. As the founding evaluation team member, you'll lead the development of automated dashboards and user studies to measure model performance. This role offers the chance to shape the evaluation culture of a fast-growing startup.

🎯 What You'll Do

• Design evaluation pipelines for models in development and production
• Design user studies for subjective model evaluations
• Convert requirements into measurable metrics
• Design and develop automated evaluation dashboards

📋 Requirements

• Metric design experience for model performance evaluation
• User study design on platforms like Mechanical Turk
• Model training and fine-tuning for evaluation purposes
• Statistical analysis to compare evaluation results

✨ Nice to Have

• Experience with ASR and TTS model training
• Experience with large-scale ML (3B+ models, >1M hours data)

🎁 Benefits & Perks

• 🏖️ Remote-first work environment
• 💰 Competitive compensation
• 📈 Growth opportunities as founding team member
• 🐶 Pet-friendly culture

📨 Hiring Process

Estimated timeline: 2-4 weeks · AI estimate

1. 1Recruiter phone screen· 30 min
2. 2Technical interview· 60 min
3. 3Onsite/virtual final round· 3 hours