The role
Job description
We’re looking for an AI Reliability Engineer who can ensure our AI agents perform reliably in production — from deployment and monitoring to incident management and continuous improvement. This role goes beyond traditional SRE. You’ll not only monitor whether systems are running but also ensure AI agents are delivering the right outcomes. What You’ll Be Responsible For: Manage AWS cloud infrastructure, including Amazon Bedrock. Build and maintain CI/CD pipelines and Infrastructure as Code. Implement AI agent observability using OpenTelemetry and LLM monitoring tools. Monitor system performance, latency, errors, costs and AI quality. Manage safe deployments, canary releases and automated rollbacks. Handle incident response, on-call support and postmortems. Implement security, encryption, access controls and compliance measures. Optimize model performance, token usage, rate limits and provider fallbacks.
Qualification(s)Desired Experience
3-5 years
Location
Chennai
Desired SkillsCompensation & Benefits
As per the industry standard
About the Company
On behalf of one of our clients who are in the space of Gen AI building systems in the healthcare vertical focussed for US markets