SlipstreamJobsFresh Startup & VC-Backed Jobs

Sr Staff Software Engineer ( AI Agents, Observability)

ServiceNow - Santa Clara, CA, United States - Hybrid - posted 2026-10-06

Apply on the company site

SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.

Salary: USD 190,900 - 334,100 / annual

ServiceNow is seeking a Senior Staff Software Engineer to join the AI Agents for Observability group. This team is building a new generation of AI agents designed to transform how enterprises investigate, respond to, and remediate critical incidents and alerts. The mission is to reduce mean time to resolution (MTTR) by orders of magnitude, turning reactive firefighting into proactive, intelligent automation. The AI agents for Observability platform combines the intelligence of large language models, the predictive power of observability analytics, and the judgment of human incident commanders within a single governed process running on ServiceNow's enterprise-grade platform. This dramatically reduces the time and expertise required to triage multi-service incidents and enables organizations to maintain SLOs as infrastructure complexity grows. In this role, you will: - Design and architect the next generation of intelligent incident and alert investigation and remediation systems, enabling enterprises to automate away toil and focus on innovation - Drive technical direction for assigned projects, defining architecture, design patterns, best practices, and leveraging the latest AI/ML models for integrations - Collaborate with product managers, software engineers, UX designers, and security experts to build product features that meet business objectives and security standards - Lead architecture reviews and technical decision-making on high-impact initiatives spanning multiple teams - Create tools, libraries, and frameworks for other developers to build upon - Stay current with industry trends and emerging technologies to drive innovation and improve the platform - Mentor and influence engineering excellence across the incident intelligence domain, helping colleagues apply emerging agentic patterns responsibly Qualifications: - 12+ years of experience building scalable software applications using Java or a similar object-oriented programming language - Strong experience with JavaScript or TypeScript and modern frontend engineering practices - Strong foundation in data structures, algorithms, object-oriented design, and performance optimization - Proven expertise in multi-agent systems design: orchestration frameworks, agent communication patterns, state management across distributed agents - Practical experience integrating foundation models and LLMs into production systems, with awareness of hallucination, latency, cost, and safety trade-offs - Proven ability to solve significant technical problems with broad impact across teams or product areas - Demonstrated expertise in architecture, technical strategy, and driving complex initiatives from design through delivery - Experience mentoring engineers and influencing engineering excellence through reviews, standards, and technical leadership - Practical experience using AI-assisted coding tools to improve development workflows and engineering productivity - Strong analytical and software design skills

Similar roles