Backend Inference Framework Engineer Graduate (AML Inference) - 2027 Start
Summary
Build and optimize scalable inference systems for AI models, focusing on architecture design, performance tuning, and distributed high-concurrency deployments.
- Build scalable inference systems
- Conduct inference technology research
- Design inference service architecture
- Develop inference engine scheduling
- Implement model inference services
- Implement monitoring and alerting
- Innovate with business scenarios
- Optimize inference framework modules
- Promote distributed high concurrency architecture
- Resolve performance bottlenecks
- Resolve resource bottlenecks
- Resolve stability issues
- Select inference technologies
- Set up canary release
- Standardize technical system