Role & responsibilities
Design, develop, and deploy AI/GenAI agents using Agentic AI frameworks and LLM technologies.
Build and operationalize agent workflows for automation, incident response, RCA, deployment validation, and reliability engineering.
Deploy and manage AI solutions across hyperscaler cloud platforms (Azure, AWS, GCP) and Kubernetes settings.
Integrate agents with CI/CD pipelines, observability tools, ITSM platforms, code repositories, and enterprise systems.
Develop reusable APIs, connectors, prompt templates, and automation frameworks.
Implement AI governance controls including guardrails, access controls, audit logging, monitoring, cost optimization, and rollback mechanisms.
Own deployment, troubleshooting, observability, and continuous improvement of AI agent platforms.
Collaborate with DevOps, SRE, Security, Platform, and Engineering teams to deliver production-ready solutions.
Preferred candidate profile
5+ years of experience in Software Engineering, Cloud Engineering, DevOps, SRE, AI/ML Engineering,
or related roles.
Robust programming skills in Python with experience building AI/GenAI applications.
Hands-on experience with LangChain, LangGraph, Agentic AI frameworks, and LLM technologies.
Experience deploying AI/GenAI solutions in production environments.
Strong understanding of:
Prompt Engineering
RAG
Vector Databases
Tool Calling
Agent Orchestration
Structured Outputs
Robust experience with one or more Hyperscalers: Azure, AWS, or GCP.
Hands-on experience with:
Kubernetes (AKS/EKS/GKE)
Docker
Terraform
GitHub Actions / Azure DevOps / Jenkins
CI/CD and Infrastructure as Code (IaC)
Experience with observability and monitoring tools such as Grafana, Prometheus, OpenTelemetry, Splunk, Dynatrace, or Datadog.
Understanding of DevOps, SRE, cloud reliability, security, and operational best practices.
📌 Forward Deployed Engineer Hyderabad (India)
🏢 Wipro
📍 India