About the role
The Machine Learning Platform team builds and maintains systems for deploying and observing machine learning models in production. The engineer in this role operates the real-time inference service, owns model deployment infrastructure, and builds model observability tools.
Our summary of the posting; the original is on the Mercury careers page.
What the posting requires
- Required
- Backend engineering
- FastAPI
- Model deployment
- Observability
- SQL
- Python
- Flask
- Model lifecycle
- Alerting
- Preferred
- Modern data stack
- Functional languages
- Real-time inference service
- Model deployment infrastructure
- Model observability
- Experimentation capabilities
These tags are our reading of the posting. They can miss something; the original posting is the reference.