I design scalable, self-healing infrastructure with a focus on integrating AI into the SRE lifecycle.
I believe the future of infrastructure isn't just about uptime, but about predictive automationโusing Large Language Models to reduce toil and interpret complex system telemetry.
| Category | Tools & Technologies |
|---|---|
| Cloud & Orchestration | AWS (EKS, VPC, S3), Kubernetes, Docker, Helm |
| Automation & IaC | Terraform, GitHub Actions, Python, Bash |
| Artificial Intelligence | Claude |
| Observability | Prometheus, Grafana |
I actively leverage AI to sharpen my SRE output:
- Synthesizing Telemetry: Using LLMs to parse and summarize high-cardinality log data.
- Infrastructure Code: Generating boilerplate Terraform and complex RegEx for observability filters.
- Operational Intelligence: Building internal tools that bridge the gap between static alerts and actionable insights.
- LinkedIn: linkedin.com/in/vanshajb10
- Email: vanshajbajaj1002@gmail.com
"99.99% is the goal; intelligence is how we get there."




