Biswajith Gopinathan

Building capabilities for Agnicio's AI-driven asset maintenance platform. This enables Proactive maintenance, minimizing disruptions and maximizing efficiency. By leveraging intelligent predictive analytics, the platform transforms traditional maintenance approaches through data-driven, predictive & proactive insights that anticipate potential equipment challenges. Architected comprehensive data pipelines for extraction, cleansing and transformation of high-volume industrial sensor data and Enterprise Asset Management (EAM) systems. Implemented sophisticated data quality frameworks to handle time-series sensor anomalies, missing values, and inconsistent maintenance records. Developed advanced ETL processes to normalize and enrich operational data for predictive maintenance models and GenAI applications, creating unified asset health indicators from disparate data sources. The solution empowers organizations to optimize resource allocation, reduce unexpected downtime, and enhance overall operational performance. Developed and deployed POC application with real-time streaming analytics solution in the part of problem sensing.

As a Senior Analytics Engineer, I leveraged my expertise in data analysis, engineering, and statistical modeling to drive data-driven decision-making. With a strong background in machine learning algorithms, data visualization techniques, and software development, I specialize in transforming raw data into actionable insights that fuel business growth and operational efficiency. My collaborative approach and effective communication skills enable me to work closely with cross-functional teams to identify opportunities, develop analytical solutions, and drive strategic initiatives.

Data Engineering, Pharmacovigilance, IDMP, MDM, Data Virtualization, Data Visualization, Advanced Analytics, Apache Spark, PySpark, Databricks The Identification of Medicinal Products (IDMP) is a master data initiative project across the European Union that is based on a set of five international ISO standards. Designed and developed analytical pipeline framework from Data ingesion, Data Extraction, Data transformation, Data virtualisation, Predictive Analytics and Visualisation using Databricks, PySpark, Azure DevOps and Power BI. Designed, developed, provided curated data to different layer of analytics team. Lead the team to implement data virtualization layer using Denodo. Used Azure Data services, Databricks, Python, Apache Spark, Pyspark, Denodo, Git, MLOps, Power BI, Panel. Work closely with the stake holders to identify the pain points for statistical and analytical problems and come up with solid and concrete framework to leverage the historical data.

Extracting, transforming, improving and integrating data, depending on the business requirements. Created data pipelines to extract data from different Azure data sources, integrated and transformed using Azure data factory and python. Assembled large, complex data sets that meet functional / non-functional business requirements. Completed historical data analysis dashboard using Power BI Dax queries. Deployed time series modelling for forecasts and experience to estimate demand for various items at various points in the product domain. Design and build publication-ready data visualizations using diverse sets of historical and on the fly prediction data results using Power BI and Panel-Holoviz open source libraries. Developed a web based dashboard application using Tornado web server deployed in Azure cloud wiht help of MLOps, CI/CD technologies. Work in a MLOPS environment managing purpose-built, highly available, distributed, scalable cloud services

Collaborate to perform data and cost analysis of raw material and chemical compounds for P&G's Soluble Unit Dose research and development team. Successfully interpreted data to draw conclusions for managerial action and strategy for cost analysis feedback of different Projects, formulas. Collaborate regularly with R&D team, develop and utilize dashboards, created web services to extract data from different data sources, effectively using Power BI and Python. Currently implementing cost prediction by analyzing the data from different sources.

The European Foundation for Management Development is an international not-for-prot association, based in Brussels, Belgium. Europe's largest network association in the eld of management development. They started using their enormous data for implementing analytics. Handled data quality, data analysis of their data for analytics team. Used Power BI for connecting to data sources, extracting data from their RDBMS and NoSQL system to visualise and identify data pattern. Generated reports as per customer requests and simulated these reports in web applications. Built elective reports to represent the story to answer business questions with the help of data. Created a python web application to implement automated solutions for their existing manual intervention jobs like document search, document clustering with help of Django web framework. Technologies used: Power BI, Python, Flask API, FileMaker Database, Postgres SQL database, Mongo DB, Elastic Search

Machine Learning Engineer responsible for creating machine learning models and retraining systems. Study and transform data science prototypes. Design machine learning systems, Research and implement appropriate ML algorithms and tools. Develop machine learning applications bu integrating using sophisticated micro / web services according to requirements, Select appropriate datasets and data representation methods. Run machine learning tests and experiments, Perform statistical analysis and fine-tuning using test results, Train and retrain systems when necessary.

I Am Tomorrow is an interactive festival for women in tech, arts, business and beyond. Idea is to discover more female role-models and share their stories with the world. Did predictive analysis on the raw data and potentially external data. Selecting features, building and optimizing classi􀃚ers and regressions using machine learning techniques. Build statistical/machine learning models to extract insights. Collaborate with subject matter experts to determine relevant data sources. This comes with the task to transform the data and make them suitable to work with. Ensure accuracy and performance in predictive results using various statistical methods with the help of python libraries.

Fire disasters are major disasters, which cause ecological, social, and economic damage. To minimize these losses, early detection of fire and an autonomous response are important and helpful to disaster management systems. Trained and tested the application with CNN, data acquisition, done all hyper parameter tuning, data augmentation technique and tested with best accuracy for train and test data.Trained model was persisted to a IoT device [Raspberrypi3] to test the image in real data which accurately predict the point of fire/smoke and provide the response with transformed values. • Working on a cost-effective fire detection CNN architecture project for surveillance camera images in forest area. Implementing an end to end integration for deep learning with hardware processing units to fulfill customer targets. working with Python, Keras, OpenCV, Deep Learning (CNN)

Working with European Commission sub contracted by European Dynamics for their prestigious Project Horizon 2020. Horizon 2020 is the biggest EU Research and Innovation program ever with nearly €80 billion of funding available over 7years (2014 to 2020) in addition to the private investment that this money will attract. It promises more breakthroughs, discoveries and world-firsts by taking great ideas from the lab to the market. Working in the development team of Evaluation phase of proposal work flow which manages complex workflows and data manipulation as per the requirement. Technologies : Java, Python, Oracle