AI Evaluation and Agent Systems Engineer

• In this role, you'll develop evaluation software for AI models and agents to verify behavior changes and support research workflows.
• Design evaluation harnesses for model behavior, tool use, and multi-step agent tasks.
• Record inputs, configurations, tool calls, and observations in structured traces.
• Build replay and regression tests for comparing system behavior before and after changes.
• Document scenarios, run instructions, results, and evaluation limits.

Syntony supports frontier AI organizations, public institutions, and private organizations with safety research, governance design, adversarial evaluation, and risk advisory.