Software Engineer - Agent Observability; Galileo

Position: Staff Software Engineer - Agent Observability (Galileo)
The application window is expected to close on: 11/04/2026

Meet the Team Galileo, now part of Cisco, is advancing how enterprises observe, evaluate, and secure AI agents. Our Agent Resilience platform helps organizations understand AI agent performance, evaluate quality, monitor token usage and costs, and implement runtime controls to improve reliability and security. As part of Cisco’s Agent Resilience Team, you’ll work at the intersection of AI, observability, security, and distributed systems.

We’re building innovative capabilities in AI observability, distributed tracing, multimodal evaluation, and agent control, with opportunities to integrate across Splunk AI Observability and Cisco’s broader technology portfolio. You’ll join a collaborative product engineering team working alongside backend and frontend engineers, AI researchers, product managers, and designers. This is an opportunity to influence the technical direction of emerging AI products, solve complex engineering challenges at enterprise scale, and shape how organizations manage and operate AI agents.

Your Impact As a Software Engineering Technical Leader on the Agent Resilience Team, you will lead the technical design and development of scalable, customer-facing products that enable enterprises to monitor, evaluate, and control AI agent behavior. You’ll combine hands-on engineering with technical leadership, driving complex initiatives across multiple engineers while guiding architectural decisions and ensuring reliable delivery. Lead the architecture, design, and delivery of large-scale backend systems supporting AI agent observability, distributed tracing, multimodal evaluation, AI metrics, and agent control capabilities.

Drive complex engineering initiatives from technical design through production deployment, coordinating work across engineers, defining technical approaches, and guiding implementation to deliver scalable, maintainable solutions.

Design and develop distributed systems, APIs, and data processing capabilities that ingest telemetry from multiple services and generate actionable insights from generative AI traces, metrics, and events.

Contribute hands-on production code in Python and/or Go, lead technical design and code reviews, mentor engineers, and drive architectural decisions that improve product performance, reliability, and engineering quality.

Collaborate with product managers, AI researchers, and engineering teams across Splunk and Cisco to deliver customer-facing capabilities. Participate in a shared on-call rotation, typically one week approximately every two months, depending on team size, to support production reliability.

Success in this role means delivering complex technical initiatives through collaboration with other engineers, establishing scalable architectures, improving production reliability, and advancing enterprise AI observability and resilience capabilities.

Minimum Qualifications Bachelor’s degree with 8+ years of related experience, or Master’s degree with 6+ years of related experience, or equivalent practical experience.
8+ years of experience developing production backend software applications and services using Python and/or Go.Experience leading the technical design and delivery of complex software systems or projects involving multiple engineers, including coordinating technical work and providing engineering guidance. Experience designing and developing distributed systems, backend architectures, and APIs for scalable, high-throughput, data-intensive applications.

Experience making technical architecture decisions involving system scalability, reliability, performance, and maintainability.

Preferred Qualifications Experience developing customer-facing products involving…