# Bijon Kumar Pramanik, M.Eng.

> AI assistants on your own data, Python and Node.js backends, Next.js apps and MT4/MT5 Expert Advisors, built by Bijon Kumar Pramanik. Freelancing since 2016.

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.

Full text of every page and article: https://cyberjon.com/llms-full.txt

## Blog posts
- [FastAPI vs Express: choosing a backend for an AI product](https://cyberjon.com/articles/fastapi-vs-express): 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.
- [How to backtest an Expert Advisor in the MT5 Strategy Tester without fooling yourself](https://cyberjon.com/articles/backtesting-ea-mt5-strategy-tester): 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.
- [How to build an AI agent with tool use on the Claude API (Python)](https://cyberjon.com/articles/claude-api-tool-use-agent): 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.
- [How to build an AI phone agent with Twilio and FastAPI](https://cyberjon.com/articles/ai-phone-agent-twilio-fastapi): Build an AI phone agent by pointing a Twilio number at a FastAPI webhook that returns TwiML, reads the caller's speech and replies with text from your LLM.
- [How to deploy a FastAPI app on AWS EC2 with Docker and Nginx](https://cyberjon.com/articles/deploy-fastapi-aws-docker-nginx): Deploy FastAPI on AWS EC2 by running it in a Docker container with Uvicorn, putting Nginx in front as a reverse proxy, and adding free HTTPS with Certbot.
- [How to make a Next.js site visible to AI search engines](https://cyberjon.com/articles/nextjs-ai-search-visibility): Make a Next.js site visible to AI search: server-render HTML, allow AI crawlers in robots.ts, add a sitemap, llms.txt and JSON-LD, then submit to Bing.
- [How to stream Claude API responses in a Next.js chat app](https://cyberjon.com/articles/stream-claude-nextjs-chat): Stream Claude's reply word by word in a Next.js App Router chat: a route handler with the Anthropic TypeScript SDK and a React client that reads the stream.
- [How to test an LLM app against real conversations](https://cyberjon.com/articles/testing-llm-apps): Test an LLM app by turning real, anonymized conversations into an eval set, scoring each reply with clear checks, and rerunning it on every prompt change.
- [OpenAI, Claude or Llama 3: how to choose an LLM for your product](https://cyberjon.com/articles/choosing-an-llm): How to choose between OpenAI, Claude and Llama 3 for a product: compare quality on your task, cost per completed task, latency, privacy and hosting, then test.
- [Prompt engineering for production chatbots: a practical checklist](https://cyberjon.com/articles/prompt-engineering-production-checklist): A production chatbot prompt needs a clear role and scope, grounding in retrieved context, a fixed output format, an "I don't know" rule, versioning and tests.
- [RAG vs fine-tuning: which one does your AI app need?](https://cyberjon.com/articles/rag-vs-fine-tuning): Use RAG when your AI app needs current facts and citations from your documents. Use fine-tuning when it needs a fixed style, format or narrow behavior.
- [Risk-based position sizing in MQL5 (with code)](https://cyberjon.com/articles/position-sizing-mql5): Size MQL5 trades by risk: lots = risk money / (stop distance in ticks x tick value), rounded down to the volume step, with a full MQL5 function.
- [Selenium vs Puppeteer: which to use for scraping and browser automation](https://cyberjon.com/articles/selenium-vs-puppeteer): Use Selenium for multi-language, multi-browser automation and Python projects; use Puppeteer for fast Chrome automation, scraping and PDF generation in Node.js.
- [What is an Expert Advisor? MT4 vs MT5 explained](https://cyberjon.com/articles/what-is-an-expert-advisor): An Expert Advisor is a program that trades automatically inside MetaTrader. Learn how EAs run, and how MT4 (MQL4) and MT5 (MQL5) differ in practice.
- [What is RAG? A practical guide to retrieval-augmented generation](https://cyberjon.com/articles/what-is-rag): RAG lets an LLM answer from your own documents by retrieving relevant chunks at question time and adding them to the prompt. Here is how it works and fails.

## Services
- [AI applications](https://cyberjon.com/services/ai-applications): 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.
- [Python & backend systems](https://cyberjon.com/services/python-backend-systems): 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.
- [Next.js web apps](https://cyberjon.com/services/nextjs-web-apps): 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.
- [MT4 / MT5 Expert Advisors](https://cyberjon.com/services/mt4-mt5-expert-advisors): 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.

## Case studies
- [Sigma7 Gold Swing](https://cyberjon.com/projects/sigma7-gold-swing) (MT5 Expert Advisor · MQL5 Market): 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. Tools: MQL5, MetaTrader 5, XAUUSD, Risk sizing. Live: https://www.mql5.com/en/market/product/195382 Backtest (MetaTrader 5 Strategy Tester, XAUUSD H1, 2026.01.08 to 2026.09.09, modeling: Every tick, deposit 1,000 USD, leverage 1:500. Risk 2% per trade, all nine streams (Trade frequency: Very high), NFP filter on.): Total net profit 9,486.22 USD; Gross profit / gross loss 16,221.55 / −6,735.33; Profit factor 2.41; Recovery factor 5.10; Sharpe ratio 8.35; Expected payoff 11.58; Total trades 819; Profit trades 692 (84.49%); Short trades (won) 398 (85.68%); Long trades (won) 421 (83.37%); Balance drawdown maximal 1,063.49 (12.76%); Equity drawdown maximal 1,860.69 (20.48%); Equity drawdown relative 28.94% (430.70); Largest profit / loss trade 1,201.10 / −223.46; Average profit / loss trade 23.44 / −52.22; Maximum consecutive losses 6 (−551.95). Backtest results do not guarantee future results.
- [No-Code AI Bot Building Framework](https://cyberjon.com/projects/no-code-ai-bot-framework) (Full-stack developer): 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. Tools: FastAPI, OpenAI, Llama 3, LlamaIndex, Twilio, MongoDB, Docker.
- [AI-Powered Financial App](https://cyberjon.com/projects/ai-powered-financial-app) (Backend developer): 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. Tools: Express, TypeScript, OpenAI, AWS, MongoDB, Puppeteer.
- [ChenChen GongHao App Backend](https://cyberjon.com/projects/chenchen-gonghao-app-backend) (Backend developer): Backend services for the Android and iOS apps. Tools: Spring Boot, Java, Oracle SQL.
- [Decentralized Identity Management](https://cyberjon.com/projects/decentralized-identity-management) (Full-stack blockchain developer): Built seif.io, a blockchain-based identity management solution, from zero. Tools: Hyperledger Fabric, Golang, Node.js, Angular, Ansible, Cloudant.
- [Blockchain Identity Management](https://cyberjon.com/projects/blockchain-identity-management) (Full-stack blockchain developer): A blockchain-based identity management solution for datachain.one. Tools: Hyperledger Fabric, Golang, Node.js, Angular, Ansible.

## Skills
OpenAI, Claude API, LLM, RAG, Python, FastAPI, MQL4, MQL5, React, Next.js, Express, MongoDB, MySQL, Docker, AWS, Hyperledger, Ansible.

## Experience
- OpenAI & Prompt Engineer, Xobot (Dec 2023 – present)
- Full-Stack Developer, Upwork (freelance) (Jun 2016 – present)
- Self-employed, Code and build something every day (Jan 2016 – present)

## Education
- Master of Engineering (M.Eng.), China University of Geosciences, Beijing (2016 – 2019)
- Bachelor’s degree, Shenyang University of Chemical Engineering, China (2011 – 2014)
- Bachelor’s degree, Hajee Mohammad Danesh Science & Technology University (2008 – 2011)
- Higher Secondary Certificate, Rajshahi Government City College (2004 – 2006)

## FAQ
### Who is Bijon Kumar Pramanik?
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.

### What does Bijon build?
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.

### Can you build an AI agent that answers from my own data?
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.

### What is RAG?
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.

### Can you build voice bots that answer phone calls?
Yes. I connect AI agents to phone calls with Twilio Programmable Voice, and turn voice messages into text with AWS Transcribe.

### Do you build MetaTrader 4 and MetaTrader 5 Expert Advisors?
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.

### How do I start a project with you?
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.

## Contact
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.

- Email: bijon@cyberjon.com
- Phone / WhatsApp: +880 1711 731367 (https://wa.me/8801711731367)
- GitHub: https://github.com/cyberjon
- LinkedIn: https://www.linkedin.com/in/cyberjoncs/
- MQL5 (Expert Advisors on the MQL5 Market): https://www.mql5.com/en/users/cyberjon/seller
- Website: https://cyberjon.com