Senior Engineer, Agentic SRE

About the role

This position is for an experienced SRE and DevOps automation specialist who aims to eliminate manual tasks by building self-healing infrastructure. You will work within the Health100 cloud ecosystem, focusing on automating alert triage. The role involves integrating Generative AI and agentic workflows into platform operations to enhance log summaries, ticket enrichment, and incident response.

Key facts

What you'll do

• Develop intelligent automation scripts using Python and Bash, and create agentic workflows for log analysis, automated failure summaries, and issue routing.
• Implement LLM orchestration tools such as LangChain, LlamaIndex, Vertex AI, and Gemini to build smart Slack bots and ticket enrichment pipelines.
• Uphold SRE principles, including service health monitoring, error budget management, and high-quality alerting for production GKE clusters.
• Design secure and auditable automation patterns that adhere to healthcare compliance and PHI handling standards.
• Serve as a technical point of contact for platform, network, database, and security teams to diagnose complex infrastructure and container issues.

Requirements

• 5 or more years of experience in Site Reliability Engineering, DevOps, or Platform Operations within complex enterprise settings.
• 4 or more years of advanced engineering experience using Python and Bash to develop API-driven tools and automation utilities.
• 3 or more years managing Kubernetes (GKE), CI/CD pipelines, and enterprise observability/telemetry systems.
• Demonstrated interest or practical experience in building agent-based automation or integrating with LLM APIs.

Nice to have

• Production experience creating operational Slack bots or automating incident post-mortems.
• Extensive understanding of modern data layers like Kafka, Redis, Oracle DB on Google Cloud Platform, or Postgres.
• Active certifications such as Google Certified Professional Cloud DevOps Engineer or CKA/CKAD.

Skills & tools

• Python
• Bash
• LangChain
• LlamaIndex
• Vertex AI
• Gemini
• Kubernetes (GKE)
• CI/CD
• Kafka
• Redis
• Oracle DB@Google Cloud Platform
• Postgres