AIOps · Agentic · Talk
OpsAI: multi-agent incident investigation
A talk on OpsAI — a multi-agent AI system for evidence-cited incident investigation and automated ops intelligence, presented at CNCG Chandigarh.
JUN 2026 · 1 MIN
Kubernetes·Multi-Cloud·AIOps
Infrastructure, Automation & AI/MLOps
Built from scratch. Run in production.
I help engineering teams ship faster by giving them infrastructure they don’t have to think about — reliable foundations on Kubernetes, reusable building blocks other teams adopt, and delivery that stays out of the way. Six years across Azure and AWS, and lately the part I enjoy most: getting AI to help run the platform — catching problems earlier, predicting incidents, and turning a messy cloud bill into plain-English answers. The goal is always the same: make the platform boring.
I build, automate, and write in this space.
CKACertified Kubernetes AdministratorVerified credential
AWS SAASolutions Architect – AssociateVerified credential
Terraform AssociateHashiCorp Certified: Terraform AssociateVerified credential
60%
less spent on observability
60 GiB
logs ingested daily
30%
cut from CI runner spend
~6 yrs
running production infra
// featured writing
GitOps · Agentic · CI/CD
Teach Your Git Log to Deploy Itself
Conventional Commits as the trigger layer for agentic CI/CD — letting the commit history drive releases instead of hand-run pipelines.
APR 2026 · 1 MIN
Kubernetes · Autoscaling
Scaling On Steroids: Karpenter
A deep dive into Kubernetes node autoscaling with Karpenter — how it provisions the right capacity fast, and where it beats the Cluster Autoscaler.
MAY 2024 · 1 MIN
// selected work
- Agentic FinOps intelligence layer for Azure, in GoA two-stage LLM pipeline: an anomaly-detection agent correlates spend spikes with infrastructure change events, and a synthesizer explains root cause in plain English.AgenticSHIPPED
- The Kubernetes foundation for a multi-cloud healthcare platformBuilt the AKS cluster on Azure + AWS as the shared foundation applications and internal tools run on — so teams get a consistent place to deploy instead of one-off setups.Evolent2024 — NOW
- A self-service developer portal with BackstageHelped bring Backstage to the org — a self-service portal so engineers can ship on their own instead of waiting on the platform team, backed by GitOps delivery and reusable release workflows.PlatformSHIPPED
- Full-stack LGTM observability with OpenTelemetryLoki, Grafana, Tempo, and Mimir on AKS with OTel and Pydantic LogFire for AI-ready ops pipelines. Same visibility, a fraction of the managed bill.−60%SPEND
- AIOps foundation: KubeFlow pipelines and KServe on AKSDeployed ML pipelines and KServe inference (Gemma) as the base for automated incident prediction and anomaly detection, aligned with SRE practice — SLOs, incident response, post-mortems.AIOpsSHIPPED