• Leading the architecture and delivery of an large-scale Agentic AI Observability Chatbot for huge Walmart network infrastructure. This system utilizes the LangGraph, ReAct and advanced RAG to translate natural language to queries or API/MCP calls. This multi-source data retrieval tool reducing MTTD and MTTR for network incidents.
• Designed and developed an anomaly detection framework using time series deep learning prediction models as a monitoring tool for data center network devices.
• Designed and developed an automation framework based on text mining to extract required data elements and feed them to other parts of network infrastructure.
• Designed and implemented a configuration framework for all the Walmart network devices around the world.
Technologies
Python, Restful API, PostgreSQL, Elastic search, Spark pipelines, Kafka, Rabbitmq, CI/CD pipeline
GCP, BigTable, Grafana