AI Engineer

You will build tools that help developers understand agent traces, evaluate agent behavior, and turn results into improvements. You will run experiments and benchmarks on AI-agent primitives, investigate performance gaps, and use your findings to improve configurations and product capabilities.

Responsibilities

• Build tools for understanding traces, evaluating agent behavior, and turning results into improvements
• Run experiments on agent primitives and benchmarks
• Investigate performance strengths and gaps
• Improve agent configuration and behavior based on evaluation findings
• Turn research findings into capabilities developers can use

Requirements

• Experience shipping agents and agentic applications into production
• Experience tuning agents to improve accuracy
• Ability to benchmark results against existing datasets or create datasets intelligently

Benefits

• Fully remote work