About the role
Primary Skills
- Observability: ELK (Elasticsearch/Kibana), Prometheus, Grafana, PromQL
- Automation: Java/Vert.x or Python (FastAPI), Shell/Bash, REST/SOAP APIs
- Cloud & Platform: Docker, Kubernetes, Kafka, Redis
- Reliability Engineering: Distributed Systems, Microservices, Event-Driven Architecture, DR & Incident Management
- Stakeholder Management & Cross-functional Collaboration
Secondary Skills
- Agentic AI: LangChain, LangGraph, RAG, MCP
- LLM Integration & AI Frameworks
- Python (FastAPI)
Key Responsibilities
- Build and deploy LLM-powered Agentic AI solutions with tool calling and autonomous workflows.
- Integrate AI capabilities into existing applications using modern AI frameworks.
- Own platform reliability through SLAs, SLOs, error budgets, MTTD/MTTR, and operational governance.
- Enhance observability using ELK, Prometheus, Grafana, and advanced alerting.
- Lead incident response, RCA, disaster recovery, and resiliency initiatives.
- Drive production readiness, automation, platform stability, and infrastructure optimization.