
Sensi is an AI-powered career intelligence platform that helps students and job seekers understand their true skill profile and measure fit against real job opportunities with high-resolution semantic analysis.
Job seekers often lack an objective way to measure how their credentials align with complex role requirements. Existing tools are fragmented—resume builders don't providing scoring, and job boards lack deep semantic analysis. For students, rich academic histories are often ignored by keyword-based filters, leaving their true potential invisible.
Sensi leverages Large Language Models (LLMs) to perform structured skill extraction from both resumes and academic transcripts. It constructs a multi-dimensional competency profile across Technical Skills, Domain Knowledge, Soft Skills, and Academic Rigor. This profile is then visually cross-referenced against job descriptions in real-time.
Built in under 12 hours, Sensi was an exercise in extreme prioritization. The core challenge was designing a 'radar-first' layout where a 6-axis chart remains the hero of the UI. I focused on building a 'progressive disclosure' model where advanced features—like AI-generated cover letters and specific resume edit recommendations—only unlock once a high fit score (65+) is achieved, ensuring users focus on roles where they have genuine alignment.
Deep parsing of resumes and transcripts into structured competency profiles using Gemini and OpenAI.
A visual centerpiece using Chart.js that overlays user profiles against job requirements for instant alignment feedback.
Real-time fit scoring directly over LinkedIn, Indeed, and Handshake job postings using Chrome Storage and content scripts.
Automatic generation of personalized cover letters and resume-edit suggestions triggered by high fit scores.
Achievement
Vibe ATL @ Georgia Tech
Timeline
March 2026