Sr. SDE Devops Engineer

Job Summary

We are looking for a Senior DevOps Engineer with strong experience in cloud-native infrastructure, Kubernetes, CI/CD, Infrastructure as Code, production reliability, and cloud security to support the deployment and operation of AI/LLM-based applications and agent platforms.

The role will focus on building and operating production-grade AI infrastructure and agentic systems, including agent-native/LLM agent frameworks, scalable deployment platforms, automation, observability, reliability, and end-to-end production ownership.

The ideal candidate should be comfortable working across AWS and Azure, with hands-on expertise in Python, Kubernetes, Docker, Terraform/IaC, Linux, networking, CI/CD, and SRE practices. Strong production troubleshooting and customer communication skills are also important.

Job Description

Key Responsibilities

• Design, build, and maintain cloud-native infrastructure for AI/LLM applications and agent-based systems.

• Deploy, operate, and scale production-grade LLM agents and agent frameworks.

• Develop and maintain Kubernetes-based platforms for highly available and scalable workloads.

• Build and optimize CI/CD pipelines for application and AI/agent deployments.

• Automate infrastructure provisioning and configuration using Terraform and Infrastructure as Code (IaC).

• Work across AWS and Azure cloud environments to deploy and manage production workloads.

• Implement SRE practices covering reliability, availability, scalability, incident management, and operational readiness.

• Establish and maintain observability using metrics, logs, traces, dashboards, and alerting.

• Monitor production systems and proactively identify performance, reliability, and capacity issues.

• Troubleshoot complex production, infrastructure, networking, Kubernetes, and cloud-related issues.

• Implement cloud security practices covering identity, access management, secrets, network security, container security, and secure deployments.

• Develop automation and operational tooling using Python and scripting.

• Work closely with engineering, AI/ML, product, and customer-facing teams to ensure successful production deployments.

• Take end-to-end ownership of production environments, from deployment and monitoring through incident resolution and continuous improvement.

• Participate in incident response, root-cause analysis, post-incident reviews, and reliability improvement initiatives.

• Help define standards and best practices for cloud-native architecture, platform automation, security, and production operations.