🛠 Tech Stack

💼 About This Role

You'll shape evaluation metrics for speech LLMs and automated quality scoring in a fast-growing AI startup.

🎯 What You'll Do

• Design and build evaluation harnesses for speech LLM checkpoints
• Define measurable benchmarks for speech model capabilities
• Own dashboards tracking model health during training
• Debug performance regressions across model and infrastructure

📋 Requirements

• Python proficiency and experience with distributed systems
• Ability to translate ambiguous concepts into automated metrics
• Experience with data pipelines or evaluation harnesses at scale
• Strong communication of statistical results to stakeholders

✨ Nice to Have

• Experience with speech metrics like WER, CER, PESQ
• LLM-as-a-Judge evaluation experience
• Human evaluation and crowdsourcing management

🎁 Benefits & Perks

• 💰 Competitive Compensation: $180K - $270K base + bonus + equity
• 🏖️ Unlimited PTO plus 13 paid holidays
• 🏥 Top-tier healthcare including dental and vision
• 👶 12 weeks paid parental leave
• 💻 Choice of top laptops/workstations

📨 Hiring Process

Estimated timeline: 2-4 weeks · AI estimate

1. 1Recruiter Screen· 30 min
2. 2Technical Interview· 60 min
3. 3Onsite Interview· 120 min