Open to opportunities

Vedant Nakshane

@vedantnakshane

Message

I’m an AI SRE engineer building AI-powered incident detection and automated remediation.

India

Message

What I'm looking for

I want to build AI-driven observability and incident automation in production environments, partnering with SRE/ops stakeholders to reduce MTTD/MTTR and ship reliable, auditable systems with measurable impact.

I’m an AI Engineer and Site Reliability Engineer focused on production outcomes: AI-powered incident detection, root cause analysis, and automated remediation. I bridge customer reliability challenges and engineering execution, translating insights into measurable, deployed improvements.

At Bajaj Finserv, I built and deployed an AI SRE platform that integrates Prometheus and Grafana across 50+ microservices to detect, diagnose, and auto-remediate incidents. I configured and optimized detection with enterprise operations stakeholders, adapting alerting thresholds and correlation logic to specific microservice topologies.

I also built production incident automation that integrates with ServiceNow for AI triage and routing, and implemented RAG pipelines with FAISS to ground responses in customer-specific operational context. In fast-moving, ambiguous rollout scenarios, I debugged integration failures, resolved data quality issues in real time, and maintained zero unlogged incidents with full audit traceability.

Beyond incident automation, I create observability extensions—aggregating infrastructure, cost, and pricing signals from AWS into unified intelligence layers and routing queries through an MCP gateway with centralized validation, logging, and access controls. I bring an engineering ethos of precision, urgency, and reusable systems that help teams achieve reliability with confidence.

Experience

Work history, roles, and key accomplishments

AI Engineer - SRE & GenAI

Bajaj Finserv

May 2025 - Jun 2026 (1 year 1 month)

Built and deployed an AI SRE platform for incident detection, root cause analysis, and automated remediation across 50+ microservices. Partnered with enterprise operations stakeholders and developed Python-based automations to extend observability and reliability workflows.

Prometheus Grafana AWS Python Incident Response Root Cause Analysis Anomaly Detection

OpsBot – AI SRE Platform

Bajaj Finserv

Built and deployed an AI SRE platform integrating Prometheus and Grafana across 50+ microservices to detect, diagnose, and auto-remediate incidents. Performed AI-driven root cause analysis and worked with enterprise stakeholders to tune alerting and correlation logic.

Prometheus Grafana AWS Python Incident Response Root Cause Analysis Anomaly Detection

Cloud Monitoring Bot

Bajaj Finserv

Developed observability automation aggregating infrastructure, cost, and pricing signals across 12+ AWS accounts into a unified intelligence layer. Implemented an MCP gateway with validation, logging, and access controls, containerized with Docker, and deployed on AWS EC2 with CI/CD.

AWS Python fastAPI Docker MCP Scripting GitHub Actions

ITOPS Bot - Incident Automation

Bajaj Finserv

Owned end-to-end customer deployment of production incident automation integrated with ServiceNow, including configuration and production readiness. Built Python automations using RAG with FAISS to ground responses in customer operational context and reduce resolution time.

Python AWS fastAPI ServiceNow Deployment RAG Faiss

AWS Org & GenAI Admin

Bajaj Finserv

Owned AWS Organization infrastructure governance for a GenAI team, including IAM governance, VPC network controls, SCP enforcement, and multi-account security architecture. Delivered production-ready, correctly scoped AWS infrastructure for AI SRE deployments with zero security incidents.

AWS Cloud Infrastructure IAM VPC Network Controls Security

Azure AI Foundry - Deployment

Bajaj Finserv

Guided 20+ enterprise customer deployments from scoping and integration through production readiness using AI agents configured on Azure AI Foundry. Translated customer insights into product enhancements and built Python automations extending the AI platform across customer codebases and knowledge systems.

Azure LangGraph Python Scoping