Sheldon Sequeira Email & Phone Number

Maharashtra, India

India

• Spearheaded MLOps with Vertex AI, training BigQuery ML model, tracking in Vertex Experiments, deploying to an endpoint, and enabling real-time Model Monitoring for operational and data drift detection on GCP which improved workflow process by 50% for a leading US client.

• Integrated MLOps solution with Azure DevOps CI/CD using Sonarqube for generating code coverage report on a remote VM instance.• Led a team of four, implementing data and model validation, unit testing, fairness/bias, explainable AI algorithms for an in-house MLOps product.• Developed MLOps solution in Azure Databricks, utilizing MLflow and inhouse model serving capabilities.• Implemented MLOps POC, deploying ML model on a remote VM using MLflow, Docker, and Kubernetes.• Successfully integrated and deployed an app having angular as frontend and django as backend using nginx on a remote VM instance.• Implemented unsupervised learning techniques to build Early Warning System which increased operational efficiency by 40% by helping clients identify employee churn rate faster.

Mumbai, Maharashtra, India

• Actively strategizing the digital platform design to capture relevant customer data for future incorporation of advanced analytics for the PaaS (Platform as a Service) model of the company.• Automated internal business procedures and designed a standardized structure for the master database.• Built a customized retrieval based chatbot for the digital platform during its pre-launch stage.

Bengaluru, Karnataka, India

• Inspecting and cleaning DW-MRI brain scan images before training it on a DL model for an AI product that identifies if a patient is suffering from brain cancer or not using live patient's MRI scan as streaming data.• Responsible for building workable data pipelines by implementing latest research concerning DW-MRI data of the brain.

United States

• Developing and testing hypothesis related to financial health index variables.• Analyzed $1+ billion in transactions to determine user behaviour.• Suggested new strategies for improving the visualization of the financial app dashboard which increased the consumer app open rate by 2.3% after 2 months.

Bengaluru, Karnataka, India

Presented my research titled "Comparisons of Stock Price Predictions Using Stacked RNN-LSTM" at ICInPro 2021 where this research focuses on how neural networks such as the LSTM (Long Short-Term Memory) model can be employed to understand price changes, interest patterns and trades in the stock market sector. The datasets of companies such as IBM, Cisco, Microsoft, Tesla and GE were used to build the stacked RNN-LSTM model using timesteps of 7 and 14 days. The two layered stacked RNN-LSTM models of the companies such as Microsoft and Tesla achieved their highest model accuracies after being trained over a span of one year whereas the other companies acquired their highest accuracies after being trained over a span of 4 to 5 years which implies that the rate of change of economic factors affecting Microsoft and Tesla over a short span of time is high as compared to the other existing companies.

Master'S Degree, Data Science

Bachelor'S Degree, Mathematics