About the role
The team builds and enhances a system for evaluating software agents. The engineering director leads the core team, improving agent performance validation and applying agentic engineering techniques to production.
Our summary of the posting; the original is on the G2 careers page.
What the posting requires
- Required
- Python
- FastAPI
- OpenAI
- Claude Code
- Java
- Node.js
- Anthropic
- Codex
- Kotlin
- Preferred
- Agent tool use
- STATE-Bench
- Playwright
- Temporal
- AWS E2B
- MCP servers
These tags are our reading of the posting. They can miss something; the original posting is the reference.