AI Orchestration / Platform Engineer
Summary
Designs and builds the infrastructure that routes, monitors, and scales AI models in production, including observability, orchestration, and security gates.
- Build model gateway and model routing
- Create observability for traces metrics and costs
- Design orchestration patterns for multi step agents
- Develop platform templates SDKs and reference pipelines
- Handle production incidents and root cause analysis
- Implement durable state and checkpoints
- Implement secrets and identity integration
- Integrate CI CD and environment promotion
- Integrate infrastructure as code and policy as code
- Optimize performance concurrency throughput and caching
- Set up automated quality and security gates