DevOps · AWS · Docker · CI/CD

Push to production,
automatically.

I’m Balaji. This site is the demonstration: a commit to main is built, tested and deployed to AWS in under a minute — no manual step, no key on the server, and a rollback that happens on its own if the new version is unhealthy.

Selected work

Automated CI/CD deployment pipeline

Designed, built and operated solo

A push to main builds a Docker image, smoke-tests it against the routes the site actually serves, publishes it to Amazon ECR under an immutable commit-SHA tag, then replaces the container on EC2 through AWS Systems Manager. There is no SSH key, no inbound SSH rule, and no credential stored on the server. If the new container never answers /healthz, the previous image is restored automatically and the pipeline still fails — a recovery is not a pass.

  • 40–55 scommit to live
  • 1reachable port
  • 0credentials on EC2
  • Autorollback, verified
  • GitHub Actions
  • Docker
  • Amazon ECR
  • Amazon EC2
  • AWS Systems Manager
  • IAM least privilege
  • Nginx
  • Bash

More write-ups are on the way. Each one follows the same format as above: what it does, what it cost, what broke.

What I work with

Delivering and running

  • Docker — images, layers, multi-stage builds
  • GitHub Actions — jobs, dependencies, gated deploys
  • AWS — EC2, ECR, IAM, Systems Manager
  • Nginx — static serving, container config
  • Linux — Ubuntu, systemd, permissions, TCP checks

Foundations

  • Git — branching, commit history as the release version
  • Bash — scripts that fail loudly and clean up after themselves
  • YAML — pipeline definitions read by machines, reviewed by humans
  • Least privilege — every identity scoped to one resource
  • Cost awareness — right-sized instances, lifecycle policies

What I would build next on this

Education

Contact

Open to DevOps and cloud engineering roles. The fastest way to judge the work is to read the case study, then look at the source.