App LogoApp name
SP

Saurabh Pramanik

Open to work0 years experience

Software Engineer

Noida, Uttar PradeshTarget Roles: Backend Engineer • Full-Stack Developer • Frontend Specialist

CS final-year student with experience in AI-powered web apps and scalable backend services.

GitHubLinkedIn
Resume
Email

Standing Rank

Rank Not Available

Developer Badges

Badges Pending

Skills & Technologies

25 skills
c++javascriptpythonsqlreact.jscss3vitenode.jsexpress.jsrest apiswebsocketspostgresqlredisawsdockerlinuxrag pipelinespgvectorvector searchllm integrationdata structures & algorithmsoopoperating systemsgithubpostman

Work Experience

Frontend Development Intern

Unified Mentor Pvt Ltd

Jul 2025 - Aug 2025 Noida, Uttar Pradesh
  • Developed and optimized 30+ reusable React components using React.js and Vite, reducing frontend development effort by 15% and improving UI consistency across the product
  • Built responsive, cross-browser web applications and refactored component architecture to improve reusability and reduce code duplication

Projects

GhostApply — Agentic AI Job Search Engine

View Project
React.jsNode.jsPostgreSQLpgvectorRedisDockerPlaywrightAWS
  • Designed and developed an agentic AI platform that autonomously discovers jobs, performs semantic resume matching, researches companies, and drafts personalized outreach workflows
  • Built a Retrieval-Augmented Generation (RAG) pipeline using PostgreSQL + pgvector embeddings and LLM-powered scoring to improve JD-to-resume matching relevance by 40%
  • Optimized application workflows by 80% through asynchronous multi-agent pipelines handling automated scraping, deep company research, and high-relevance draft generation.
  • Deployed on AWS with Docker, Redis queues, and CI/CD pipelines supporting asynchronous automation

Kritique — AI Code Review System

View Project
Node.jsExpress.jsReactPostgreSQLPrismaRedisBullSSEDocker
  • Built a full-stack AI code review platform supporting 10 programming languages, delivering structured severity-classified feedback with token-level streaming and persistent review history
  • Designed a queue-driven backend architecture using Bull + Redis, processing 20 concurrent review jobs without request drops by decoupling API latency from LLM inference
  • Reduced perceived latency by 70% via SSE-based token streaming, delivering the first response token in 800ms compared to 8–12s full-response time
  • Implemented a fault-tolerant 3-state circuit breaker system to prevent cascading failures during Redis outages with automated fail-fast recovery

CollabCode — Real-Time Collaborative Code Editor

View Project
React.jsNode.jsExpress.jsSocket.ioYjsMonaco EditorRedisJWT
  • Engineered a low-latency collaborative editor using Yjs CRDT and Socket.io, enabling conflict-free simultaneous editing with sub-100ms synchronization latency
  • Developed a real-time distributed system with Redis-backed persistence for sessions, messaging, and file synchronization across server restarts
  • Designed dual-mode architecture (Personal + Interview) with JWT + GitHub OAuth, role-based access control, sandboxed execution via Judge0 (14 languages), and Groq Llama 3.3 70B for context-aware AI assistance

Leaderboard Standings

Leaderboard Position Pending

Global test scores, peer standing percentiles, and algorithm leaderboard ranks are updated dynamically.

Assessment Highlights

Assessments Not Completed

Coding evaluations, system assessment results, and conceptual score badges will appear here after taking a test.

AI Collaboration Score

AI Collaboration Score Pending

Developer coding behavior, assistant cooperation, and AI pair-programming indicators are evaluated during live coding sessions.

Role Compatibility Profile

Role Compatibility Analysis Pending

Custom matching reports, candidate role compatibility percentiles, and core engineer strength profiles are processed once conceptual code screenings are complete.

Achievements

Quantum vs. Classical Elman Neural Networks for Stock Market Prediction

Submitted to IEEE, 2026: Comparative study of Classical ENN, QENN-Qiskit, and QENN-Q# for stock forecasting across 6 global datasets.

About Details

Professional Bio

CS final-year student with hands-on experience building AI-powered web applications, real-time collaborative systems, and scalable backend services. Proficient in React, Node.js, TypeScript, PostgreSQL, and Redis.

Bachelor of Technology in Computer Science

Jaypee Institute of Information Technology (2022 - 2026)

Languages: English, Hindi
Email: Locked