The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Back to feedPost
Autonomous AI Career Intelligence Platform
Overview
I developed an autonomous AI-powered platform designed to automate the job discovery and evaluation process.
The system continuously analyzes job opportunities against a candidate profile and delivers ranked recommendations directly through Telegram.
Rather than relying on manual job searches, the platform transforms fragmented opportunities into actionable career intelligence.
⸻
The Challenge
Job seekers often spend significant time reviewing opportunities that are poorly aligned with their qualifications, experience, or career goals.
The objective was to create a system capable of:
Monitoring opportunities continuously
Evaluating candidate-job fit automatically
Ranking opportunities by relevance
Delivering personalized recommendations in real time
⸻
Solution
Intelligence Layer
Developed a scoring engine that evaluates:
Technical skills alignment
Professional experience relevance
Industry compatibility
Education requirements
Soft skills fit
Each opportunity receives a weighted score and detailed evaluation breakdown.
⸻
Recommendation Layer
Beyond numerical scoring, the platform generates contextual insights explaining:
Why a role is a strong match
Which qualifications are missing
Potential competitive advantages
Areas for improvement
This transforms raw job data into actionable decision support.
⸻
Infrastructure
The platform operates as an autonomous workflow deployed on Render.
Key capabilities include:
Automated opportunity monitoring
Data processing pipelines
AI-driven evaluation
Telegram notification delivery
Continuous 24/7 execution
⸻
Operational Workflow
Candidate submits CV
System extracts and analyzes profile information
Opportunities are collected and processed
Matching engine evaluates compatibility
Ranked recommendations are delivered automatically
AI-generated insights explain each result
⸻
Key Features
✅ Automated CV Analysis
✅ AI-Powered Matching Engine
✅ Explainable Scoring System
✅ Real-Time Job Monitoring
✅ Telegram-Based Delivery
✅ Continuous Cloud Deployment
⸻
Outcome
This project demonstrates my ability to design and deploy production-ready AI workflows that bridge the gap between complex technical systems and real-world efficiency.
The result is an autonomous platform that reduces manual effort while improving the quality and relevance of career opportunities presented to the user.
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Related posts
AI Assistant Using Your Business Knowledge Base — RAG on Your Documents
THE PROBLEM
Q&A bots break down when knowledge lives in documents: a 100-page manual has no "questions" to match, it can't fit into a prompt, and generic chatbots hallucinate instead of admitting what they don't know.
THE SOLUTION
A RAG (Retrieval-Augmented Generation) knowledge base: documents are split into meaningful chunks, embedded into a vector index, and the assistant answers from the right sections — by meaning, not keywords.
Any format as-is: PDF, DOCX, TXT, Markdown — 100+ pages is fine
Answers grounded in YOUR documents — it says "I don't have that information" rather than inventing
Source references — every answer shows which document and section it came from
Runs on your infrastructure — documents never leave your control
One command to re-index after updating documents — documented, no programmer needed
LIVE DEMO
Ask it about my products, pricing, deployment and support — it answers from 6 real documents with sources:
https://kb-assistant-demo.dvc-ai.workers.dev
The 'I don't have that information' line is the part most RAG builds skip, and it's the one that matters. How do you set the cutoff? On mine, a fixed similarity threshold broke once I filtered results by user role. Scores shifted and it refused questions it could answer.
I worked on a motion design for mtesthub.
A platform that makes hiring easier for recruiters.
the lime and navy combo looks good. did you do the brand too or just the motion?
Automated a manual Google Sheets → Slack workflow to eliminate repetitive data entry and give the team instant notifications.
Previously, new data had to be manually checked, processed, and shared across the team — slow and easy to miss. I built a Make.com scenario that:
Watches Google Sheets for new/updated rows
Processes and routes the data through a router based on conditions
Creates corresponding Trello cards for task tracking
Logs processed records back to Google Sheets
Sends real-time Slack notifications so the team is instantly updated
Result: What used to be manual checking and updating is now fully automated — saving hours weekly and removing room for human error.
Tools: Make.com, Google Sheets, Trello, Slack
wow love this