About the role
The team ensures the reliability and efficiency of systems that serve AI models to users. The engineer operates and scales these production systems, manages model rollouts, and partners with research teams to deploy new techniques.
Our summary of the posting; the original is on the Thinking Machines Lab careers page.
What the posting requires
- Required
- Python
- Observability
- Rollout process
- Productionize
- Incident response
- Graceful degradation
- Capacity management
- Go
- Monitoring
- Models
- Preferred
- Deployment systems
- Inference techniques
- Rollout systems
- Cost optimization
- Batching
- Canarying
These tags are our reading of the posting. They can miss something; the original posting is the reference.