L2 Production Support engineer (Gen AI/LLM Based Applications)

We are looking for an experienced L2 Production Support Engineer to provide operational support for AI-driven and enterprise software applications. The role requires strong problem-solving skills, a deep understanding of modern application stacks (frontend, backend, cloud, and integrations), and the ability to ensure high availability, reliability, and performance of production systems.

Key Responsibilities

• Provide L2 support for production applications, ensuring minimal downtime and quick resolution of incidents.
• Perform incident triage, root cause analysis, and issue resolution for application, infrastructure, and integration-related problems.
• Monitor application health using logs, alerts, dashboards, and proactively prevent potential failures.
• Support CI/CD pipeline deployments, rollback handling, and environment stability.
• Work with cloud platforms (AWS, Azure, GCP) to troubleshoot issues with deployed services.
• Collaborate with L3 engineering teams for complex problem resolution and permanent fixes.
• Ensure adherence to security protocols (OAuth, SSO, Entra ID, Okta) in production environments.
• Maintain and troubleshoot Docker/Kubernetes-based deployments.
• Support varied integration patterns (REST, SOAP, gRPC, Web Sockets, Batch, Webhooks).
• Perform performance tuning, load testing analysis, and optimization of applications.
• Maintain documentation of issues, resolutions, runbooks, and support procedures.
• Participate in an on-call rotation to provide 24x7 support for critical applications.

Required Experience & Skills

• Bachelor’s/Master’s degree in Computer Science, Engineering, or related field.
• 5–8 years of experience in Production Support or Application Support (L2 role).
• Strong hands-on experience with:
• Frontend & backend stacks: React JS, Next JS, Java, .NET, Python
• Cloud platforms: AWS, Azure, GCP
• CI/CD tools & VCS: Git, branching/merging, pipelines
• Containers & Orchestration: Docker, Kubernetes
• Integration troubleshooting: APIs (REST/SOAP), gRPC, WebSockets, batch jobs

Beneficial / Nice-to-Have

• Experience with Generative AI/LLM-based applications and related platforms (Azure AI Studio, AWS Bedrock, Hugging Face).
• Exposure to RAG pipelines, data ingestion, cleansing, and evaluation.
• Knowledge of IaC tools such as Terraform/Ansible for environment setup.
• Experience supporting large-scale, data-driven AI/ML applications.

E-mail resume to srinivas.adepu@p99soft.com