Site Reliability Engineer (GCP & Agentic AI)

UST; Bengaluru; On-site; INR 3,000,000 - 5,200,000; Full time

Job summary

UST is seeking a hands-on Site Reliability Engineer to ensure production services are reliable, observable, and continually improving. The role spans batch, streaming, microservices, AI/ML model serving, LLMOps pipelines, and agentic systems.

The ideal candidate brings proficient-level expertise in GCP and agentic AI, using AI to improve observability and incident investigations. You will validate AI-generated operational artifacts and production outcomes.

Qualifications

• Hands-on SRE with focus on reliability and observability across production services.
• Experience with AI/ML production systems and agentic AI is a plus.

Responsibilities

• Own reliability initiatives end to end across production applications on GCP.
• Apply agentic AI to observability design and incident investigations.
• Evaluate AI-generated runbooks and recommendations for production use.
• Validate AI-generated artifacts before production and maintain accountability.
• Identify reliability gaps and observability blind spots proactively.
• Ensure observability and human-in-the-loop for AI/ML systems.
• Drive continuous improvement of production reliability and practices.
• Lead incidents with calm communication alongside Platform/ML/Data teams.
• Mentor junior SREs on responsible operational practices.

Skills

GCP

Agentic AI

Job description

Role Description

We are looking for a hands-on Site Reliability Engineer responsible for ensuring production services are reliable, observable, and continuously improving. This role focuses on services including batch, streaming, microservices, AI/ML model serving, LLMOps pipelines, and agentic systems.

Role Description

We are looking for a hands-on Site Reliability Engineer responsible for ensuring production services are reliable, observable, and continuously improving. This role focuses on services including batch, streaming, microservices, AI/ML model serving, LLMOps pipelines, and agentic systems.

The ideal candidate brings Proficient-level expertise in GCP and agentic AI, using AI and agent-based capabilities responsibly to improve observability, incident investigation, operational workflows, and service reliability. The SRE remains accountable for validating AI-generated operational artifacts and production outcomes.

Key Responsibilities

• Own reliability initiatives end to end across multiple production applications on GCP, from issue detection and root-cause analysis through lasting remediation.
• Apply agentic AI to observability design, operational workflows, and incident investigations, including orchestrating agents and sub-agents.
• Use sound judgment when evaluating AI-generated runbooks, s, monitoring analysis, and operational recommendations.
• Validate AI-generated artifacts before they are introduced into production and maintain clear accountability for operational outcomes.
• Identify reliability gaps, cascading failure risks, SLO burn threats, and observability blind spots proactively.
• Ensure AI/ML production systems have appropriate observability and human-in-the-loop escalation paths.
• Drive continuous improvement of production reliability and operational practices.
• Lead calmly and communicate clearly during incidents while collaborating effectively with Platform, ML, and Data teams.
• Guide junior SREs in responsible operational practices and help maintain high reliability standards across the team.

Skills

GCP, Agentic AI