Backend Inference Framework Engineer Graduate (AML Inference) - 2027 Start
Summary
Build and optimize AI model inference services for high-performance, scalable deployment, focusing on architecture, performance tuning, and distributed system stability.
- Design inference service architecture
- Diagnose performance bottlenecks
- Implement canary release
- Implement inference engine scheduling
- Implement model inference services
- Improve stability under high concurrency
- Optimize distributed high concurrency service architecture
- Optimize inference framework core modules
- Select and innovate inference technologies
- Set up monitoring and alerting
- Standardize technical system