Skip to content
View pjha26's full-sized avatar
🎯
Focusing
🎯
Focusing
10 followers · 7 following

Achievements

Achievement: Pull SharkAchievement: YOLO

Achievements

Achievement: Pull SharkAchievement: YOLO

Highlights

  • Pro

Block or report pjha26

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
pjha26/README.md

👨‍💻 About Me

class Pushkar:
    def __init__(self):
        self.role = "Final-Year CS (AI & ML) Engineer"
        self.focus = ["Multi-Agent Systems", "RAG", "Distributed Backends", "Full-Stack"]
        self.flagship = "ArthAI — Multi-Agent B2B Lead Generation Platform"
        self.currently_learning = ["Distributed Systems", "System Design", "Kubernetes"]
        self.looking_for = "AI-first / Full-Stack Internships @ Startups & Product Companies"

    def say_hi(self):
        return "Let's build something that thinks 🧠⚡"
  • 🧠 Building ArthAI, a multi-agent B2B lead-generation platform — actively deployed and evolving in production
  • 🎙️ Built MockMind, an AI voice interview platform powered by LangGraph state machines
  • ⚙️ Full-stack across React/Next.js, Node.js/FastAPI, Postgres/Mongo, and LLM-driven agent workflows
  • 📈 Deep-diving into Distributed Systems, System Design, Backend Scalability & Kubernetes
  • 🏏 165+ LeetCode problems solved

🚀 Featured Projects

🧠 ArthAI

Multi-Agent B2B Lead Generation Platform

My flagship, production-deployed project — specialized AI agents research, qualify, and score leads end-to-end.

  • Multi-agent pipeline: Gemini + Groq-hosted Llama 3.3 70B fallback
  • RAG-powered lead qualification across multiple pgvector stores
  • ML intent scoring (scikit-learn) served on FastAPI
  • Competitor intel & news signal enrichment
  • BullMQ + Redis background jobs, Slack/Discord HOT-lead alerts
  • Deployed: Vercel · Railway · Supabase · Upstash

Next.js FastAPI PostgreSQL Prisma Redis BullMQ Gemini Groq pgvector

🎙️ MockMind

AI Voice Interview Platform

Voice-based AI interviewer running behavioral, technical, system-design, and HR flows in real time.

  • Real-time voice interaction via Vapi
  • LangGraph interview state machine (Evaluation → Strategy → Question Gen)
  • Groq-hosted Llama 3.3 70B inference + Gemini
  • HMAC-signed sessions, JWT auth
  • Transcript + structured feedback persistence

Next.js PostgreSQL Prisma LangGraph Groq Vapi JWT

📐 SpecForge

AI Technical Specification Platform

Turns GitHub repos or plain-language ideas into structured technical specs.

  • Multi-model routing: OpenAI + Gemini
  • Streaming generation via Server-Sent Events
  • OpenAPI 3.1 contracts, GitHub sync & webhooks
  • AI-powered document chat over generated specs
  • Exports: DOCX, PDF, Markdown, Notion, code scaffolds

React TypeScript Vite Node.js Express PostgreSQL Drizzle SSE

⚡ ExpertBook

Real-Time Expert Booking Platform

Experts define event types, clients book sessions with live availability.

  • Sub-100ms real-time updates via Socket.io
  • Server-side availability validation, timezone-aware scheduling
  • JWT auth with role-based access control
  • Gemini-powered expert matching & session summaries
  • Calendar .ics export

React Vite Node.js Express MongoDB Socket.io JWT Gemini

🛠️ Tech Arsenal



OpenAI Gemini Groq LangGraph RAG pgvector scikit--learn MLflow

📊 GitHub Analytics

🐍 Contribution Snake

Animated via a scheduled GitHub Action — see .github/workflows/snake.yml below.

🏆 Trophy Case

🎯 What I'm Looking For

I'm actively seeking software engineering & AI/ML internships — AI-first and full-stack roles at startups and product companies where I can ship agentic systems, backend infra, and applied ML.

📫 Email · LinkedIn · GitHub


Pinned Loading

  1. ML-Backend ML-Backend Public

    Real-time AI-powered student concentration monitoring system using MediaPipe, OpenCV, FastAPI, and React with live attention tracking, gaze analysis, and interactive analytics dashboard.

    JavaScript

  2. real-time real-time Public

    A production-ready booking system for professionals. Features custom event types, real-time availability via Socket.io, Gemini AI matching, and automated meeting links.

    JavaScript

  3. vc-intelligence vc-intelligence Public

    TypeScript

  4. arth.ai arth.ai Public

    AI-powered Intelligence CRM that auto-generates deep-dive research reports for inbound leads using a multi-agent Gemini/Groq pipeline with RAG chat and ML-based intent scoring

    TypeScript

  5. Spec-Forge Spec-Forge Public

    TypeScript

  6. mock-mind mock-mind Public

    AI-powered voice mock interview platform with adaptive follow-ups, LangGraph conversation engine, and real-time voice interaction using Vapi

    TypeScript