Staff Engineer, AI Agent Observability & Resilience

Cisco Systems, Inc.; San Jose (CA); On-site; USD 187,000 - 268,000; Full time

Benefits offered by this job

Life insurance

Vision insurance

Parental leave

Paid holidays

Sick time

401(k)

Job summary

Cisco Systems, Inc. in the San Jose area is seeking a Staff Software Engineer for Agent Observability (Galileo) to lead the design and development of scalable backend systems supporting AI agent observability and resilience.

You will contribute hands-on coding in Python and Go, mentor engineers, and drive architectural decisions while collaborating with product managers, AI researchers, and other Cisco teams to deliver enterprise-grade observability capabilities.

Qualifications

• 8+ years of production backend software experience in Python and/or Go.
• Experience leading multi-engineer design and delivery.
• Experience with distributed systems and scalable APIs.
• Architecture decisions focused on scalability and reliability.

Responsibilities

• Lead the architecture, design, and delivery of large-scale backend systems supporting AI agent observability and resilience.
• Drive complex engineering initiatives from technical design through production deployment.
• Design and develop distributed systems, APIs, and data processing capabilities ingesting telemetry from multiple services.
• Contribute hands-on production code in Python and/or Go, lead technical design and code reviews, mentor engineers, and drive architectural decisions.
• Collaborate with product managers, AI researchers, and engineering teams across Cisco to deliver customer-facing capabilities; participate in on-call rotations.

Skills

Backend development

Python

Go

Distributed systems

Technical leadership

Code reviews

Education

Bachelor’s+ Exp

Master’s+ Exp

Job description

Cisco Systems, Inc. in the San Jose area is seeking a Staff Software Engineer for Agent Observability (Galileo) to lead the design and development of scalable backend systems supporting AI agent observability and resilience.

You will contribute hands-on coding in Python and Go, mentor engineers, and drive architectural decisions while collaborating with product managers, AI researchers, and other Cisco teams to deliver enterprise-grade observability capabilities.