Feb 2025 - Mar 2025
Sep 2024 - Feb 2025
Jul 2024 - Sep 2024
Jan 2023 - Jun 2023

Forecasting and Mathematical Modelling for Detection, Prediction and Correction of issues in production plants

Python
Databricks
Mathemathical algorithms
PowerBI
PySpark
Feb 2025 - Mar 2025
During this fast-paced 4 weeks RFP I worked closely in sprints with my team to complete a solution with forecasting models and mathematical modelling algorithms to power a dashboard enabling the company to get insights and predictions to enhance their production yields.

Goals:

  • Designed a mathematical algorithm to enhance SAP-generated information based on real-time machine sensors.
  • Implemented jobs & pipelines in Databricks to allow an efficient forecasting and data processing stream.
  • Worked on developing data quality standards and IoT issue spotting
  • Built the processing backend to collaborate with colleagues in creating RT and Historical PowerBI dashboards.

Algorithmic Solution for Material Traceability and Batch Analytics System

Python
Azure Functions
Differential Algorithms
CI/CD
PowerBI
SQL
Azure DBs
Sep 2024 - Feb 2025
In this project, we primarily focused on developing an accurate mathematical model to identify efficiency bottlenecks linked to financial losses, enabling the site team to proactively address issues before incurring significant economic costs. Information was delivered to client via an intuitive collection of dashboards with deep analysis on their productions and schedules.

Goals:

  • Designed a track & tracing algorithm, resulting in a substantial reduction in cost analysis discrepancies and improved accuracy in financial assessments.
  • Integrated Azure Functions for scalable data processing.
  • Implemented CI/CD pipelines for automated deployment and integration testing with 98.5% coverage.
  • Created data insights with PowerBI dashboards connected to Azure SQL Databases.

High-Performance ML Model Enhancement and Code Optimization

Python
Azure ML Studio
Azure DB
XGBoost
Azure Functions
ETL
Refactoring
Jul 2024 - Sep 2024
Contributed to a mature project by boosting efficiency and model performance through strategic refactoring, documentation, and model retraining.

Goals:

  • Refactored codebase using hashmaps for efficient O(1) lookups.
  • Retrained models with XGBoost to improve R² scores.
  • Enhanced algorithm robustness with additional logic layers.
  • Implemented a data quality assurance module with the team.

ASGI-Based GenAI Platform for Seamless LLM Integration

Python
FastAPI
Microsoft Bot Framework
Azure
ASGI
Pytest
Langchain
Streamlit
Jan 2023 - Jun 2023
Built a modular solution with a frontend, gateway, router, and SDK for GenAI agents, enabling seamless interaction with databases, audio, images, and documents, adding ML and CV capabilities.

Goals:

  • Implemented multi-server ASGI architecture for GenAI, reducing server costs and enhancing latency.
  • Optimized LLMs with additional features such as function calling, audio, and custom image & document processing, decreasing operator KT time and increasing factory output.
  • Developed predictive maintenance ML models and implemented them with GenAI agents.
  • Deployed microservices and databases on Azure.
  • Implemented custom LLM agents using Azure Bot Framework to allow seamless deployments in MS Teams, Slack, and other platforms.