Inspiration
I'm a second-year CSE student. I have 3 deployed projects, 150+ open source PRs, and a GitHub that updates almost every day. But when I applied for internships, I was sending out the same 1-page resume as everyone else — generic bullet points, no real metrics. The problem isn't that students don't have skills. It's that their resumes don't show them.
What it does
PixelForge is a Live Developer Identity Platform. Instead of manually writing a resume, you connect your GitHub. PixelForge syncs your real work, extracts skills, and when you paste a job description, it generates a tailored 1-page resume in 30 seconds. It writes real bullets — "Reduced API latency by 40%" instead of "hardworking team player".
How I built it (Nebius & NVIDIA Integration)
- Frontend: Next.js 15, Tailwind CSS, Clerk for auth.
- Backend: FastAPI, PostgreSQL (Neon), SQLAlchemy.
- AI Integration: For this hackathon, I integrated the Nebius Token Factory and routed AI generation through NVIDIA Nemotron models, with a fallback to Gemini and Groq. This ensures enterprise-grade reasoning for matching user repos to complex job descriptions.
- Embeddings: sentence-transformers for semantic matching.
The AI layer uses a router that picks the best model per task. Every AI call is logged to an AI usage dashboard so the user can see cost, latency, and token usage.
Challenges
- GitHub API rate limits — unauthenticated calls are capped at 60/hour. Added a token for 5,000/hour.
- Semantic matching — matching repos to job descriptions needed embeddings, not keyword search.
- Multi-model routing — building a fallback chain using Nebius/Nemotron so the product doesn't break if one API goes down.
What I learned
- Building with real tools beats building in a sandbox.
- AI is a force multiplier. The AI wrote the boilerplate. I wrote the logic and made the product decisions.
Built With
- ai
- clerk
- fastapi
- llm
- nebius
- nemotron
- next.js
- nvidia
- postgresql
- python
- react
