Software Engineer
Core
Design, build, and deploy core capabilities for Cisco's next-generation AI-powered Production Intelligence platform, combining SRE practices with agentic AI to monitor, diagnose, and auto-remediate global SaaS infrastructure.
Role type
Senior Software Engineer (SRE & Agentic AI)
Builds
AI-assisted observability systems, automated incident response tools, and self-healing cloud infrastructure
Domain
Cloud Infrastructure & AI/ML Operations
Deliverable
production ML models
Required skills
Python, Go, Java, C++, Kubernetes, Docker, SRE practices, microservices design, API design, distributed systems
Preferred skills
LLM pipelines, Model Context Protocol (MCP), RAG architectures, OpenTelemetry, Prometheus, Terraform, Kafka, Redis, PostgreSQL
Technologies
Python, Go, Java, C++, Kubernetes, Docker, OpenTelemetry, Prometheus, Grafana, Splunk, AWS, GCP, Azure, Terraform, Jenkins, GitHub Actions, Kafka, Redis, PostgreSQL, Elasticsearch
Responsibilities
Design high-resilience software systems for AI-assisted observability; Build and maintain production-grade AI agents and MCP tool integrations; Implement telemetry ingestion and correlation pipelines; Develop proactive anomaly detection and Human-in-the-Loop remediation workflows; Define SLIs/SLOs and lead post-incident reviews; Mentor mid-level and junior engineers
Seniority
Senior, hands-on IC with mentorship responsibilities