AssemblyAIRemote
Research Engineer, Evaluations
New York, United States of America
Full Time
6 days ago
$210,000 - $260,000 USD
No Visa Sponsorship
Key skills
PythonMachine LearningMLLeadership
About this role
Role Overview
- Own model evaluation across accuracy, latency, and metrics
- Build benchmarking pipelines
- Design experiments to measure model impact
- Manage evaluation datasets
- Define real-world performance metrics
- Summarize findings for leadership
Requirements
- Machine Learning / Research Engineering background
- Strong Python skills
- Understanding of ML models
- Familiarity with voice agent components
- Comfortable interpreting technical results
- 3-4 hours overlapping with Eastern US Time Zone
- Ownership mindset
Tech Stack
- Python
Benefits
- Pay Transparency
- Equal opportunity to succeed