An automated career optimization pipeline and job application dashboard built with Python, FastAPI, Google Cloud Firestore, and Vertex AI (Gemini 1.5 Flash). Created for the Google Cloud Code Kitchen reality series auditions.
- Astra Multimodal Vision AI Scanner: Project Astra-inspired scanner using Gemini Vision to parse handwritten job posters, screenshots, and hiring flyers to auto-extract Job Title, Company, Required Skills, and Compensation.
- Zapier Webhook & Gmail Automation: RESTful Webhook listener (
POST /api/webhook/zapier) that integrates with Zapier triggers to automatically ingest, parse, and log incoming job application emails from Deloitte, Amazon, and LinkedIn. - Firestore Database Integration: Deploys as a native serverless backend storing jobs inside document collections on Google Cloud Firestore, with an automatic local SQLite fallback for local-first testing.
- Vertex AI Resume Analyzer: Leverages Gemini to run semantic analysis against a candidate's resume, calculate an ATS match score, extract missing keywords, and suggest optimizations.
- AI Follow-up & Cold Mailer: Instantly drafts tailored cold pitches and follow-up templates based on the specific job description and application stage.
- Premium Glassmorphic Interface: A fast, responsive, and gorgeous dark-mode dashboard with real-time stats and visual funnel trackers.
flowchart TD
A["Job Seeker"] -->|Interacts| B["Glassmorphic Frontend"]
B -->|API Requests| C["FastAPI Backend (Cloud Run)"]
C -->|Read/Write Logs| D["Google Cloud Firestore"]
C -->|Structured JSON Prompt| E["Vertex AI (Gemini 1.5 Flash)"]
C -->|Cron Alerts| F["Cloud Scheduler & Tasks"]
Navigate to the directory:
cd C:\Users\adiqu\.gemini\antigravity\scratch\ai-job-trackerSet up your virtual environment and install packages:
python -m venv venv
source venv/Scripts/activate # On Windows: venv\Scripts\activate
pip install -r requirements.txtCreate your .env file (already initialized in root) and set your Gemini API key and Firestore project ID:
GEMINI_API_KEY=your_gemini_api_key_from_google_ai_studio
FIRESTORE_PROJECT_ID=ai-job-tracker-kitchenLaunch the development server:
uvicorn app.main:app --reloadOpen http://127.0.0.1:8000 in your browser to view the live dashboard!
To deploy the application to your pre-funded Google Cloud Sandbox:
gcloud init
gcloud config set project [YOUR_PROJECT_ID]Use Google Cloud Build to package the container and deploy it serverless:
gcloud run deploy ai-job-tracker --source . --port 8000 --allow-unauthenticatedMade with ❤️ for the Code Kitchen Auditions.