Senior Director - AI Evaluation Platform

ServiceNow•Santa Clara, CA

1d•Remote

About The Position

The CoreAI team, part of the Platform and AI organization, is focused on building the evaluation infrastructure and frameworks that ensure the quality, reliability, and safety of AI capabilities across ServiceNow's platform. Our evaluation systems power the quality assurance behind ServiceNow's GenAI offerings, enabling our customers to trust the AI capabilities they depend on. As a Senior Director, AI Evaluation Platform, you will lead the teams responsible for building and scaling ServiceNow's evaluation platform — both internal-facing (used by research and engineering teams) and customer-facing (enabling customers to assess and monitor AI quality in their environments). Your leadership will be critical in establishing rigorous, scalable evaluation methodologies that raise the bar for AI quality across the industry. This is a fast-growing, high-impact role where you will: Lead and scale a team of talented researchers, applied researchers, and evaluation engineers building next-generation AI evaluation infrastructure. Define the strategy and roadmap for the evaluation platform, encompassing benchmark design, automated scoring pipelines, verifier systems, and quality monitoring frameworks for both internal and customer-facing use cases. Drive innovation in evaluation methodologies, including developing new approaches for agentic evaluation, multi-turn assessment, domain-specific benchmarking, and confidence calibration. Design and implement a comprehensive verifier stack spanning LLM-as-judge, rule-based, reference-based, and process verifiers to enable robust, multi-signal evaluation across diverse AI capabilities. Architect and deliver a unified evaluation platform that serves internal model development teams and external customers, with robust APIs, dashboards, and reporting capabilities. Collaborate with cross-functional teams across product, engineering, and research to translate business needs into evaluation requirements and deliver impactful quality assurance solutions. Stay ahead of the curve by researching and implementing the latest advancements in AI evaluation, including novel verifier architectures, safety and alignment evaluation, and emerging evaluation standards.

Requirements

Experience in leveraging or critically thinking about how to integrate AI into work processes, decision-making, or problem-solving. This may include using AI-powered tools, automating workflows, analyzing AI-driven insights, or exploring AI's potential impact on the function or industry.
Extensive experience in leading and managing high-performing AI or platform engineering teams, with a focus on evaluation, quality assurance, or testing infrastructure at scale.
Deep technical expertise in AI evaluation methodologies, including benchmarking frameworks, automated scoring systems, verifier design (LLM-as-judge, rule-based, reference-based, process verifiers), and statistical methods for assessing model quality, safety, and reliability.
Proven track record of building and operating production-level evaluation platforms or AI infrastructure at scale.
Strong leadership and management skills with the ability to inspire and grow a world-class team, with extensive experience managing large organizations of 50 or more engineers and researchers.
Excellent communication and collaboration skills to work effectively with stakeholders at all levels, from technical teams to senior executives.
Hands-on experience with major deep learning frameworks like PyTorch or TensorFlow and familiarity with evaluation tooling ecosystems.

Nice To Haves

A Ph.D. or Master's degree in Computer Science, Machine Learning, or a related field is a plus.

Responsibilities

Lead and scale a team of talented researchers, applied researchers, and evaluation engineers building next-generation AI evaluation infrastructure.
Define the strategy and roadmap for the evaluation platform, encompassing benchmark design, automated scoring pipelines, verifier systems, and quality monitoring frameworks for both internal and customer-facing use cases.
Drive innovation in evaluation methodologies, including developing new approaches for agentic evaluation, multi-turn assessment, domain-specific benchmarking, and confidence calibration.
Design and implement a comprehensive verifier stack spanning LLM-as-judge, rule-based, reference-based, and process verifiers to enable robust, multi-signal evaluation across diverse AI capabilities.
Architect and deliver a unified evaluation platform that serves internal model development teams and external customers, with robust APIs, dashboards, and reporting capabilities.
Collaborate with cross-functional teams across product, engineering, and research to translate business needs into evaluation requirements and deliver impactful quality assurance solutions.
Stay ahead of the curve by researching and implementing the latest advancements in AI evaluation, including novel verifier architectures, safety and alignment evaluation, and emerging evaluation standards.