ABHISHEK.PANDEY

Open to internships and freelance work

Abhishek Pandey

Backend & AI developer

I build backend systems and AI-powered applications — RAG pipelines, LLM integrations, APIs and the automation around them. Two years of freelance and open-source work alongside a Computer Science degree.

01

Who I am

I am a Computer Science undergraduate with just over two years of hands-on experience in freelance development and open-source work, focused on AI and machine learning, generative AI, retrieval-augmented generation, cloud computing and full-stack development.

Most of what I build is backend: scalable applications in Python and Java using FastAPI, Flask, Spring Boot and REST APIs, with LLMs, vector databases and cloud platforms wired in where they earn their place. The work has ranged from AI-powered consultancy tools to internal HR systems, and the through-line is turning a stated business problem into something that actually runs in production.

Alongside that I work steadily on data structures and algorithms, and on system design — the parts that do not show up in a demo but decide whether the thing survives its second month.

Languages  English, Hindi

02

What I build with

AI / Machine learning

Retrieval-Augmented Generation, LangChain, LLM APIs, Pinecone, Cohere, Fine-tuning

Backend

FastAPI, Flask, Spring Boot, REST APIs

Cloud & tools

AWS, Oracle Cloud, Git, GitHub, Postman, VS Code

Computer science

Data structures and algorithms, Object-oriented programming

Languages

Python, JavaScript, Java, C++, C, SQL, HTML, CSS

03

Things I have built

AI-Powered Study Abroad Consultancy Platform

A retrieval-augmented conversational system for a study-abroad consultancy, answering applicant questions from the firm's own documents instead of a generic model's guesswork.

  • 92% Precision@3 and 0.89 NDCG in retrieval evaluation
  • Pinecone vector store with Cohere embeddings
  • Groq for low-latency generation
  • Python
  • Flask
  • Pinecone
  • Cohere
  • Groq
  • RAG

EduMind AI

An educational platform that reads a PDF and answers questions about it in context, rather than making the student search it.

  • PDF parsing and contextual question answering in one pass
  • FastAPI backend with LLM API integration
  • Python
  • FastAPI
  • LLM APIs

AI Video Answer & Rendering Engine

A pipeline that turns a typed question into a rendered video answer — script, narration and final cut, unattended.

  • Query to structured script to narration to rendered video
  • Puppeteer and FFmpeg orchestrated from TypeScript
  • TypeScript
  • Puppeteer
  • FFmpeg

FLCS Employee Management System

An HR system covering five workflows a small company runs every week: attendance, leave, salary, task assignment and employee administration.

  • Five HR workflows in one application
  • Attendance, leave, salary, tasks and employee records
  • Python
  • REST APIs
  • SQL
04

Where I have worked

05

Where I studied

06

Competitions and roles

07

Courses and credentials

08

Get in touch

The fastest route is email. Tell me what you are building and where it is stuck — I read everything and reply either way.