AI Engineer, Agentic Systems & AI Infrastructure
Summary
AI Engineer responsible for building feedback loops for agent reliability, conducting human-in-the-loop reviews, defining metrics and guardrails for unattended agents, designing long-running agents for growth workflows, evaluating new models/tools/frameworks, implementing evals/assertions/state management/self-correction, maintaining AI knowledge hub routing and freshness, optimizing context for L
- Build feedback loops for agent reliability
- Conduct human-in-the-loop reviews
- Define metrics and guardrails for unattended agents
- Design long running agents for growth workflows
- Evaluate new models tools and agent frameworks
- Implement evals assertions state management self correction
- Maintain AI knowledge hub routing and freshness
- Optimize context for LLM workflows
- Reduce AI costs with monitoring and model routing