Looking for a job

Arnab Pandey

@arnabpandey

Full-Stack Developer building AI agents and production web apps, including NINA, an embeddable AI product assistant SDK.

India

Message

I built NINA, an AI product assistant SDK that embeds in SaaS dashboards and supports onboarding, Q&A, and workflow execution. I designed its JavaScript and TypeScript API and created a live demo deployed on Vercel.

As a Freelance Full-Stack Developer, I develop web applications and AI-powered tools, including Velvet Bid, a real-time auction platform with Gemini AI features. At Learning Temple, I’m designing database architecture and data pipelines for an ed-tech platform using MongoDB and PostgreSQL.

Experience

Work history, roles, and key accomplishments

Current

Database Engineer

Current

Learning Temple

Jul 2026 - Present (3 months)

Designing and managing database architecture for an ed-tech platform, handling schema design, query optimization, and data integrity across MongoDB and PostgreSQL. Building scalable data pipelines and contributing to backend infrastructure.

MongoDB PostgreSQL Database Design Query Optimization Data Pipelines

Current

Freelance Full-Stack Developer

Current

Self Employed

Jan 2024 - Present (2 years 9 months)

Developing production-grade web applications and AI-powered tools for clients, including auction platforms, gaming apps, and SaaS dashboards. Actively freelancing since 2024 with a portfolio of live, revenue-oriented products.

MERN Next.js Socket.IO Clerk Razorpay Gemini Claude APIs

Full Stack Web Development Intern

Labmentix Pvt. Ltd.

Feb 2026 - Aug 2026 (6 months)

Working as a full-stack SDE contributing to product development, feature implementation, and software architecture. Building and maintaining web applications using modern JavaScript frameworks and backend technologies.

JavaScript React NodeJS MongoDB PostgreSQL Git GitHub Actions Docker Vercel Render

AI Trainer

Handshake AI

May 2026 - Jul 2026 (2 months)

Trained and fine-tuned AI models by curating high-quality datasets, annotating outputs, and evaluating model responses for accuracy and relevance. Provided structured feedback on LLM outputs to improve instruction-following, factual grounding, and response quality.

AI Training Data Annotation LLM Evaluation Prompt Engineering