Shariful Islam Foysal, Developer in London, United Kingdom
Shariful is available for hire
Hire Shariful

Shariful Islam Foysal

Verified Expert  in Engineering

Bio

Foysal is a data science and applied machine learning professional with extensive experience in data analytics, statistical analysis, machine learning, and data engineering. He has experience working in a successful startup and a tech giant with a massive volume of data.

Portfolio

Amazon
Amazon Web Services (AWS), Microsoft Excel, Amazon QuickSight, Tableau...
Pathao
Microsoft Excel, TensorFlow, Tableau, Python, Data Scraping, C#, Data Modeling...
Pi Labs Bangladesh LTD
Selenium, Scrapy, OpenCV, Python, Machine Learning, Statistics

Experience

  • Data Science - 8 years
  • Machine Learning - 7 years
  • Python - 7 years
  • React - 5 years
  • Data Extraction - 5 years
  • SQL - 4 years
  • Chatbots - 3 years
  • Large Language Models (LLMs) - 2 years

Availability

Part-time

Preferred Environment

Visual Studio Code (VS Code), GitHub, Linux, MacOS

The most amazing...

...thing I've built is a complete model for real-time dynamic pricing for one of the largest ride-hailing platforms in South Asia.

Work Experience

Business Intelligence Engineer

2020 - PRESENT
Amazon
  • Engineered a Text to SQL generation service using LangChain and Claude LLM featuring a Slack bot interface for users and a web app for RAG knowledge management. The solution serves 500+ users, reducing query development time by 2,500 hours monthly.
  • Led the development of an enterprise web app using React and AWS services that automated catalog management for 400,000+ products. Implemented access control, real-time validation, and analytics dashboard, saving 10,000+ hours annually.
  • Built an LGBM-based ML model for new product demand forecasting. The solution predicts 6-month aggregated demand for products with 6-12-month lead times, enabling data-driven inventory decisions and improving forecast accuracy over heuristic methods.
  • Engineered automation system that evaluates deal eligibility across global marketplaces processes inventory, profitability, and dynamic pricing logic, generating optimized deals that reduced manual effort by 500+ hours and improved decision accuracy.
  • Built Quicksight dashboards monitoring data quality metrics across global marketplaces. The solution tracks completeness, vendor terms, and buying attributes for 400,000+ products, enabling data-driven decisions and improving operational efficiency.
Technologies: Amazon Web Services (AWS), Microsoft Excel, Amazon QuickSight, Tableau, Redshift, Python, Data Mining, ChatGPT, Data Modeling, Chatbots, Machine Learning, eCommerce, Artificial Intelligence (AI), LangChain, Large Language Models (LLMs), Retrieval-augmented Generation (RAG), React, JavaScript, Node.js

Data Scientist, Machine Learning

2018 - 2020
Pathao
  • Built machine learning (ML) models for demand prediction. Improved data extraction processes.
  • Built ​end-to-end​ ​ETL pipelines​ for real-time analytics.
  • Designed statistical experiments, ​A/B tests, ​ and multi-armed bandit tests.
  • Built ​automated​ ​FinOps Tableau, Google Sheets, and Excel dashboards​ for regular business health monitoring.
  • Developed an ML model-based tool for ​user segmentation and experimentation​ for incentive burn optimization.
  • Automated processes​ for drivers' payments, which saved 1,250 man-hours.
  • Built a financial forecasting platform combining Python ML back end with Excel interface. The system processes historical data to generate predictions, enabling business leaders to track and adjust forecasts for strategic planning.
Technologies: Microsoft Excel, TensorFlow, Tableau, Python, Data Scraping, C#, Data Modeling, Machine Learning, A/B Testing, Google BigQuery, Google Cloud, Statistical Analysis

Research Engineer

2017 - 2018
Pi Labs Bangladesh LTD
  • Developed a license plate recognition system using an image processing technique in the automated parking system.
  • Built a web scraping bot to collect information on the target user base from different sources for use in digital marketing.
  • Developed a Tesseract-based custom OCR solution to extract specific information from image documents.
Technologies: Selenium, Scrapy, OpenCV, Python, Machine Learning, Statistics

Research Associate

2017 - 2017
Dingi Technologies LTD
  • Improved GPS signal accuracy by 8% from vehicle tracking devices by implementing the Kalman Filter.
  • Designed a fuel measurement system for a vehicle tracking device.
Technologies: C, Python, Machine Learning

Experience

LLM-based Slack Bot for Natural Language to SQL Query Generation

Architected and implemented an enterprise-grade conversational AI solution that transforms natural language questions into SQL queries, enabling non-technical users to access complex database insights. Built using LangChain and Amazon Bedrock, the solution implements Retrieval-Augmented Generation (RAG) architecture to ensure accurate query generation based on business context and data schemas.

The system features a user-friendly Slack bot interface for query requests and a React web application for knowledge base management. Implemented robust security controls through authentication and built automated guardrails for query validation and blocking harmful content. The solution is highly scalable and deployed in the cloud.

Achieved significant business impact by reducing query development time by 2,500 hours monthly and democratizing data access across the organization. The system serves 500+ users and maintains high accuracy through continuous feedback mechanisms and automated performance monitoring.

Real-time Dynamic Pricing Engine for a Ride-hailing Platform

Designed and implemented an automated dynamic pricing system that optimizes revenue and market efficiency for a ride-hailing platform. The solution combines real-time supply-demand forecasting with intelligent price adjustment algorithms to maximize driver availability and rider satisfaction.

Built a robust machine learning pipeline using time-series forecasting models to predict hyperlocal demand and supply patterns. Implemented an adaptive pricing algorithm considering multiple factors, including historical patterns, current market conditions, weather impact, and special events. The system processes real-time data streams to adjust prices dynamically, ensuring optimal market balance across different city zones.

The architecture leverages containerized microservices for scalability, with automated model retraining pipelines and A/B testing capabilities. Implemented comprehensive monitoring and alerting systems to track key performance metrics,s including driver utilization, rider wait times, and market equilibrium indicators.

New Product Demand Forecasting System

Architected and developed a machine learning (ML)-based demand forecasting system for new product launches in retail. The solution utilizes LightGBM to predict 6-month aggregated demand for products with long lead times (6-12 months), enabling data-driven inventory and sourcing decisions.

Built an end-to-end ML pipeline that processes historical sales data, product attributes, and market indicators to generate accurate demand predictions. The system incorporates multiple granularity levels of product attributes and seasonality patterns to handle the cold-start problem inherent in new product forecasting. Implemented a specialized version (2.0) for newly launched products, with modified feature engineering and hyperparameter optimization.

The solution significantly improved forecast accuracy over traditional heuristic methods, enabling better inventory planning and reducing stockouts while optimizing working capital. The system processes forecasts across multiple European marketplaces, supporting strategic product design and supply chain planning decisions.

Education

2013 - 2017

Bachelor's Degree in Electrical and Electronic Engineering

Bangladesh University of Engineering and Technology (BUET) - Dhaka, Bangladesh

Certifications

NOVEMBER 2019 - PRESENT

Deep Learning Specialization

deeplearning.ai

Skills

Libraries/APIs

Scikit-learn, TensorFlow, PyTorch, OpenCV, React, Node.js

Tools

Tableau, Microsoft Power BI, Power Pivot, ChatGPT, Microsoft Excel, Apache Airflow, GitHub, Amazon QuickSight

Languages

SQL, Python, C, C#, JavaScript

Paradigms

Business Intelligence (BI), Microservices Architecture

Platforms

Linux, MacOS, Amazon Web Services (AWS), Visual Studio Code (VS Code)

Storage

MySQL, PostgreSQL, Redshift, Google Cloud

Frameworks

Flask, Scrapy, Selenium, LightGBM

Other

Data Analytics, Clustering, Regression, Data Science, Data Engineering, Google Colaboratory (Colab), Data Analysis, Algorithms, DAX, Dashboards, API Integration, Data Mining, Data Scraping, Data Modeling, Chatbots, Machine Learning, eCommerce, Grocery Delivery, Food, Google BigQuery, Data Visualization, Statistical Analysis, Web Scraping, Version Control Systems, Models, Data Extraction, Data Structures, Artificial Intelligence (AI), Statistics, LangChain, Large Language Models (LLMs), Retrieval-augmented Generation (RAG), Time Series Forecasting, A/B Testing, Demand Forecasting, RESTful Services, APIs, Web Development

Collaboration That Works

How to Work with Toptal

Toptal matches you directly with global industry experts from our network in hours—not weeks or months.

1

Share your needs

Discuss your requirements and refine your scope in a call with a Toptal domain expert.
2

Choose your talent

Get a short list of expertly matched talent within 24 hours to review, interview, and choose from.
3

Start your risk-free talent trial

Work with your chosen talent on a trial basis for up to two weeks. Pay only if you decide to hire them.

Top talent is in high demand.

Start hiring