Senior Director - AI Evaluation Platform
Core
Lead the team building and scaling ServiceNow's AI evaluation platform to ensure quality, reliability, and safety of GenAI offerings for internal teams and customers.
Role type
Senior Director, AI Evaluation Platform
Builds
Unified evaluation platform with APIs, dashboards, and reporting for internal model development and external customer use cases.
Domain
Enterprise AI / Generative AI Quality Assurance
Deliverable
production ML models | infrastructure
Required skills
AI evaluation methodologies, benchmark design, automated scoring pipelines, verifier design (LLM-as-judge, rule-based, reference-based), statistical methods for model assessment, deep learning frameworks (PyTorch, TensorFlow), team leadership for 50+ engineers
Preferred skills
Ph.D. or Master's in Computer Science or Machine Learning, experience with agentic evaluation and multi-turn assessment
Technologies
PyTorch, TensorFlow, LLM-as-judge, automated scoring pipelines
Responsibilities
Define strategy and roadmap for evaluation platform, drive innovation in evaluation methodologies, design and implement verifier stack, collaborate with cross-functional teams to translate business needs into evaluation requirements, research and implement latest advancements in AI evaluation
Seniority
Senior Director, hands-on leadership
