I help businesses and traders turn ideas into working software: AI assistants that answer from your own data, reliable backends and web apps, and MT4/MT5 Expert Advisors that trade exactly the rules you set. Freelancing since 2016.
2016
Shipping code since
EA
MT4 / MT5 in MQL
Py
FastAPI & automation
LLM
Agents, RAG & voice bots
AI assistants and agents that answer from your own documents and data, talk to your customers by chat or phone, and connect to your tools. Built on OpenAI, the Claude API or Llama 3, with retrieval (RAG) through LlamaIndex and voice through Twilio. How I build it →
The APIs, databases and automations behind your web or mobile app: built in FastAPI or Express on MongoDB or MySQL, with scraping and automation where you need it, and deployed on AWS with Docker, PM2 and Nginx. How I build it →
Fast, search-friendly web apps and dashboards in Next.js and React, with sign-in, admin panels and AI chat built in, deployed to Vercel or AWS. How I build it →
Your trading strategy turned into an MQL4 or MQL5 Expert Advisor or indicator, with position sizing and risk rules built in, and backtested in the Strategy Tester before it trades real money. How I build it →
A nine-stream swing-breakout system for gold (XAUUSD) on resting stop orders. Every trade opens with a hard stop loss and a take profit; the stop moves to break-even in profit. No grid, no martingale, no averaging.
Read the case study →View on MQL5 Market →A no-code environment for building custom AI agents on configurable LLMs, connecting different models and data sources for RAG. Twilio handles programmable voice; Google handles sign-in.
Read the case study →API for a mobile finance app with AI assistants trained on our dataset, voice-to-text through AWS Transcribe, OTP and social login, and PDF term sheets generated from Google Sheets and sent via SES.
Read the case study →Backend services for the Android and iOS apps.
Read the case study →Built seif.io, a blockchain-based identity management solution, from zero.
Read the case study →A blockchain-based identity management solution for datachain.one.
Read the case study →Choose FastAPI when your AI product leans on Python ML libraries, and Express with TypeScript when your team and frontend already live in the JavaScript world.
Read more →Backtest an MT5 Expert Advisor honestly: use real ticks, realistic costs, out-of-sample and forward data, and read drawdown and trade count, not just profit.
Read more →Build a Python AI agent on the Claude API: define tools with JSON Schema, run the tool-use loop, return results, and handle errors and stop reasons safely.
Read more →I’m Bijon Kumar Pramanik, M.Eng. Python and JavaScript are at the heart of what I do. I adapt quickly to new technology and like problems that take some untangling — front end, back end, or the logic of a trading system.
Xobot
Dec 2023 – present
Upwork (freelance)
Jun 2016 – present
Code and build something every day
Jan 2016 – present
China University of Geosciences, Beijing
2016 – 2019
Shenyang University of Chemical Engineering, China
2011 – 2014
Hajee Mohammad Danesh Science & Technology University
2008 – 2011
Rajshahi Government City College
2004 – 2006
Bijon Kumar Pramanik, M.Eng., is a self-taught full-stack developer from Rajshahi, Bangladesh. He has written code since 2016, freelances on Upwork, and works as an OpenAI & Prompt Engineer at Xobot. He holds a Master of Engineering from China University of Geosciences, Beijing.
AI applications (LLM agents, RAG and voice bots), Python and Node.js backends, full-stack Next.js web apps, and MT4/MT5 Expert Advisors for automated trading.
Yes. I build agents on OpenAI, the Claude API or Llama 3, with retrieval-augmented generation (RAG) through LlamaIndex so the agent answers from your documents and data.
Retrieval-augmented generation (RAG) lets a large language model look up relevant pieces of your own data before it answers, so the answer is based on your documents instead of only what the model learned in training.
Yes. I connect AI agents to phone calls with Twilio Programmable Voice, and turn voice messages into text with AWS Transcribe.
Yes. I turn trading strategies into MQL4 and MQL5 Expert Advisors and indicators with position sizing and risk rules built in, and backtest them in the Strategy Tester first. My EA Sigma7 Gold Swing is published on the MQL5 Market.
Send a few lines about the project by WhatsApp (+880 1711 731367) or email (bijon@cyberjon.com). I’ll reply with questions and next steps.
Tell me what you want to build and where you are with it. Send a few lines about the project and I’ll reply with questions and next steps.
Rajshahi, Bangladesh