2 months ago
Base Salary
$180k - $270k/yr
Responsibilities
- Develop clear metrics for evaluating voice naturalness and expressiveness.
- Build reliable distributed systems and data pipelines for model evaluations.
- Collaborate with ML researchers to define performance benchmarks for Speech LLMs.
- Create and maintain dashboards to track model health during training.
- Debug mid-training performance issues related to model architecture or data.
- Communicate statistical results and model behaviors to diverse stakeholders.
Requirements
- Strong software engineering skills, especially in Python.
- Experience with distributed systems and data pipelines.
- Ability to translate complex audio capabilities into measurable benchmarks.
- Familiarity with traditional and modern audio evaluation frameworks.
- Experience in managing crowdsourcing operations for human evaluation.
- Background in statistics and experimental design.
Benefits
- Competitive compensation package including base salary, performance bonus, and equity.
- Top-tier healthcare benefits for employees and dependents.
- 401(k) plan with company matching.
- Unlimited PTO and 13 paid holidays.
- 12 weeks of paid parental leave.
- Hybrid work model with a minimum of 3 in-office days per week.