Director, Network Automation & Tooling

About the role

Cboe's infrastructure footprint — and the telemetry stream it produces — is growing faster than our headcount can follow. We're hiring the leader who will close that gap with agents and intelligent automation, not more dashboards and runbooks. The Director, Network Automation & Tooling owns the strategy, architecture, and team behind the platform that lets Cboe's Operations and Engineering organizations operate at 10x their current capacity: a centralized Docker/Kubernetes backend hosting a growing fleet of AI agents, built and continuously extended with agentic coding tools such as Claude Code, that automate infrastructure operations across network, security, and telemetry domains. The intelligence layer is central to that mission. This team drives telemetry from across Cboe's global footprint — SNMP, gNMI, syslog, and API-based sources — into our Prometheus and Grafana observability platform, then builds on top of it: threshold alerting and trend analysis, and well beyond them, machine learning and agentic analysis that surface anomalies before they become incidents, correlate signals across domains, and sharpen how Operations and Engineering handle today's events and plan tomorrow's capacity. This is not a traditional infrastructure management role. It demands current technical credibility in container orchestration and infrastructure automation at scale, genuine fluency in emerging agentic AI patterns, and the leadership skill to guide subject matter experts across three domains as they extend an existing agent framework into Cboe's next-generation automation system. Agentic infrastructure engineering is being defined right now, and this leader will help define it at Cboe — setting the vision for how our network adapts to future demand, and carrying that thinking to the network and security teams who build on it and to associates across the firm. It's also hands-on. The Director stays close enough to the technology to review agent architectures, unblock hard problems, and extend the framework personally when it matters most.

Responsibilities

• Team & Organizational Leadership: Lead, mentor, and grow a multidisciplinary team of subject matter experts in network, security, and telemetry engineering, plus engineers focused on agent tooling and automation reliability. Own hiring, performance management, and career development for the automation function. Foster a culture of engineering excellence, disciplined execution, and agent-first thinking. Partner with peer Directors and VPs across Operations, Engineering, Security, and Network Engineering to align priorities and resourcing.
• Network Automation, Telemetry & Intelligent Alerting: Own the systems that deliver automated configuration deployment across the network estate — Ansible today, and whatever proves better tomorrow — including source control, staged rollout, peer review, and reliable rollback. Build and maintain automations that continuously check device configuration against approved standards and baselines, surface drift, and progressively move the organization from detection toward automated enforcement. Deliver automated software and firmware upgrade tooling with rigorous pre- and post-change validation, so upgrades are repeatable, verifiable, and safe to run at scale. Build synthetic testing automations that routinely exercise critical infrastructure services and alert Operations the moment a service degrades or becomes unavailable. Own the strategy for how network, security, and telemetry data flows into Cboe's global Prometheus and Grafana observability platform, and for the analytics and automation built on top of it. Ensure telemetry from SNMP, gNMI, syslog, and API-based polling is captured and correlated across the global network and infrastructure footprint. Set the standards for alerting on critical network events, covering thresholds, escalation paths, noise reduction, and on-call integration, in partnership with Network Engineering and Operations. Advance the use of machine learning and agentic analysis for anomaly detection, trend and capacity forecasting, and eventual auto-remediation.
• Agentic Coding & Framework Extension: Guide the technical direction of Cboe's existing agent framework, using agentic coding tools such as Claude Code to extend its capabilities. Establish engineering standards, guardrails, and review practices for agent-authored and agent-assisted changes to critical infrastructure. Stay hands-on enough to prototype, review, and unblock complex agent design and coding problems alongside the team. Champion responsible-AI practices, including human-in-the-loop controls, permissioning, and rollback safety, for autonomous agent actions. Drive advanced adoption of AI tooling across infrastructure teams, focusing first on network engineering and operations and expanding from there.
• Agentic Automation Strategy & Stakeholder Partnership: Define and own the multi-year strategic vision for using AI agents to enable Operations and Engineering to scale to 10x their current capacity. Build