Digital Twin — Conversational AI About Me
An AI twin recruiters can talk to directly about my background, skills, and projects — grounded in my actual experience rather than generic chat.
A newer version — serverless on AWS, built with Terraform and GitHub Actions — is deployed and being finalized; link coming soon.
Architecture
Conversational responses are grounded in personal/professional context and generated via Amazon Bedrock, so answers stay tied to real background rather than the model improvising. The production version runs on a fully serverless AWS architecture, with every resource defined in Terraform rather than provisioned by hand.
DevOps Practices
- CI/CD via GitHub Actions automates both infrastructure changes and application deploys, so a Terraform change and an app change follow the same reviewable, automated path
- Demonstrates infra-as-code and deployment discipline alongside the AI/RAG layer itself — the deployment process is treated as part of the product, not an afterthought
Thought Process & Design Decisions
Building this as a second, from-scratch AWS deployment (rather than just moving the Hugging Face version) was a deliberate choice to practice production-grade infra-as-code and CI/CD end to end, since that discipline is a core part of the pitch this project makes.