ServiceNow is hiring a Senior Research Scientist to build and own the core components of its AI agent evaluation platform, specifically the pipelines for running model-based judges at scale and the scoring logic that converts agent traces into actionable results.
Building something newAI / ML“We build the evaluation layer that validates AI agents before they reach customers — an automated system that scores across large volumes of agent traces.”
Product areasAI agent evaluation platform · Automated scoring of agent traces · Model-based judge pipelines · Evaluation methodologies and benchmarks for agent reasoning, planning, tool use, reliability, and safety
GoalsValidate AI agents before they reach customers · Provide results teams can act on · Measure the evaluator itself for consistency and agreement with human labels
MarketsEnterprise software (implied by ServiceNow context)
TechPython · LLM-as-a-Judge · Trajectory-based evaluation · Agentic AI · Context engineering · LLM APIs · Prompt engineering · Structured output · Synthetic and real-world datasets