End to End Machine Learning in Azure

Project Description

We are looking for a Data Scientist who has extensive experience with End to End ML in Azure

Objective:

• Create a small end-to-end demo of Azure's machine learning capabilities

Deliverables:

• Source code / notebooks that demonstrate how each service is used

• A short presentation of the findings

Project phases:

Phase 0: EDA 

• Go over a sample of the data set using Azure Machine Learning / Azure Machine Learning studio

• Understand the framework's capability to detect interactions between the dependent variable and independent variables

Phase 1: Data wrangling

• Generate a training set using Azure Databricks

• Down sample data 

Phase 2: Model building 

• Use the framework to build a model

• Deal with hyper parameter optimization

• Use out of the box feature engineering

• Display training metrics

Phase 3: End-to-end service

• Upload data to Azure data lake

• Create a model container using Azure Container Registry / Azure Container Instance

• Write a small Azure function to take some data lake records and run them through the container

We are currently only considering candidates based in the United States.