AT — 2026
0%
Full Stack · AI/ML Engineer · Open to Internships

Aditya Tripathi

I don't just write code — I ship systems that real people depend on. PRD → Architecture → Code → Deploy. Every time.

0 Lines of TypeScript
0 Active Users Served
0 Live Productions
0 Uptime on Vercel
Scroll
01 Problem Statement

Why I'm different
from the average grad.

Most CS students graduate with a resume full of claims and a GitHub full of tutorials. There's a gap between "I know React" and "I shipped a system 500 real people depend on" — and recruiters can't always tell the difference from a bullet point.

I'm a third-year B.Tech CSE student at FGIET Lucknow (CGPA 8.1/10). My approach is deliberate, not accidental.

PRD Architecture DB Schema API Contract UI Spec Ship
Note

I'd rather show you one system that's actually live than five that only run on localhost. Every claim below is backed by a live URL, a published package, or a repo you can open.

Long-Term

I'm building toward founding something myself. Right now, that means an internship where I can ship production code alongside people better than me.

02 Shipped Modules

Systems I've built
that actually run.

Every project below has a live URL, a published package, or an open repo. No localhost-only demos.

MODULE 02 · github.com/aditya1046785
AI Resume Generator
RAG Pipeline
Next.jsTypeScript Google GeminiVector Embeddings GitHub OAuth

An end-to-end RAG system that matches your real GitHub projects to a job description via cosine similarity, then writes ATS-ready bullet points from the best matches.

  • GitHub OAuth pulls repos and auto-summarizes each via Gemini
  • Embedding pipeline + cosine similarity surfaces top-fit projects with relevance scores
  • Resume writer agent turns matches into quantified, ATS-optimized bullet points
  • JSON → HTML → PDF export via headless browser rendering
View on GitHub
MODULE 03 · resume-craft-ai-rouge.vercel.app
ResumeCraft AI
Shipped
Next.jsFirebase GenKit GeminiZustandZod

A conversational resume builder — Gemini asks the questions, validates answers in real time, and assembles the resume section by section with a live preview.

  • Context-aware question engine, validated with Zod + React Hook Form
  • AI rewrites weak bullet points into stronger, quantified phrasing
  • "Fit Score" compares resume content against a job description semantically
  • Zustand-synced live preview with one-click PDF export
Visit live site
MODULE 04 · npmjs.com
AI-Metrics — LLM Usage SDK
Published Package
JavaScriptNode.js SDKTelemetry

A production-ready npm package that tracks LLM API usage — token counts, cost estimation, and privacy-safe telemetry — for OpenAI and Anthropic calls.

  • Configurable async event batching (time- or size-based flush)
  • Exponential backoff with jitter for reliable event delivery
  • Local cost-estimation engine — no external API calls required
  • Redacts API keys and secrets before transmission (GDPR-minded)
View on npm
MODULE 05 · github.com/aditya1046785
FrameSense
Real-time Framework
TypeScriptNext.js WebSocketsJWTGenKit

A real-time AI interface framework built for sub-second latency, with a full JWT auth system and modular AI orchestration via GenKit.

  • Bidirectional WebSocket layer for sub-second interactions
  • Token generation, validation middleware & refresh-token rotation
  • RESTful endpoints for users, AI interactions & data sync
  • Standardized prompt templates for modular AI feature integration
View on GitHub
03 Dependencies

Tech stack & tooling.

Languages

  • TypeScript
  • JavaScript
  • Python
  • SQL

Frontend

  • Next.js ^16
  • React ^19
  • TailwindCSS
  • Zustand

Backend

  • Node.js / Express
  • REST & WebSockets
  • NextAuth v5
  • Prisma ORM

Databases

  • PostgreSQL
  • MongoDB
  • Firebase
  • Vector DB

AI / ML

  • Google Gemini API
  • Firebase GenKit
  • RAG Pipelines
  • Vector Embeddings

Tooling

  • Git / GitHub
  • Vercel
  • Razorpay SDK
  • Zod
04 DSA Proficiency

NeetCode 150 —
structured, not random.

Built deliberately, tier by tier. Prioritizing conceptual understanding over memorized patterns. Numbers pulled live from LeetCode.

Fundamental

array ×13 string ×11 two-pointers ×7

Intermediate

hash-table ×12 sliding-window ×5 greedy ×2

Advanced

dynamic-prog ×3 div-&-conquer ×2 quickselect ×1
05 Success Metrics

Numbers that matter.

1.17M+
Lines of TypeScript Shipped
500+
Active NGO Members Served
2
Live Production Deployments
99.9%
Uptime on Vercel
📦
Published npm package AI-Metrics SDK — LLM cost tracking for production, adopted by developers.
🔗
7+ open-source repositories Documented, versioned, with CI/CD workflows on GitHub.
🤖
End-to-end RAG pipeline Ingestion → embeddings → similarity search → LLM generation, built from scratch.
💡
Active LeetCode practitioner Working the NeetCode 150 for conceptual DSA depth, not pattern memorization.
06 Revision History

The build log.

v1.0
2023
B.Tech CSE — FGIET Lucknow
Enrolled. Started from fundamentals. Built the foundation.
v1.5
2024
First Full-Stack Projects
Shipped first full-stack projects. Adopted a PRD-first workflow. Learned the cost of skipping the spec.
v2.0
2025 — Q1
Nirashray Foundation Goes Live
First production system. 500+ members. Real people depending on real code.
v2.5
2025 — Q3
RAG Pipeline + npm SDK
Built the RAG-based AI Resume Generator. Published the AI-Metrics npm package.
v3.0
2026 — Q1
ResumeCraft AI + FrameSense
Shipped two more systems. Deepened DSA via NeetCode 150.
v3.2
Aug 2026 — Now
Open to Internship — Document Under Review
Actively seeking SDE / Full Stack / AI-ML internships. Ready to ship.
07 Rollout Plan

Let's build something
that actually ships.

If this matches what you're hiring for — SDE, Full Stack, or AI/ML internship — I'm ready to start. Email is fastest.

Based in Lucknow · Open to remote · Replies within 24 hours