Data processing, analytics and machine learning at IKEA Home Smart

Developing and maintaining a Data Lake on AWS cloud infrastructure with Kubernetes, Luigi, Spark. Supporting users on the platform performing tasks within AI, ML, BI, and other processes.

Developing a Data Lake in Luigi/Spark supporting AI/ML.

Data processing pipeline development, cloud infrastructure, data platform architecture and development, and organization infrastructure are just the tip of the iceberg of responsibilities that has to be covered.As the senior engineer at a smaller company, the width of what has to be maintained is vast. Tasks include everything from an internal data platform development, to on-premise hardware acquisition and management, to account management at AWS, GCP, Jira, Slack, etc. An interesting set of work in different fields that require high levels of flexibility and multitasking.The most interesting tasks are related to data platform development and creating a cloud-agnostic system to service data scientists and customers in industry 4.0.

While doing my master thesis project, Recommender System Validation Platform, I started working part time at Expertmaker. In July 2015 I got a full time position at the company. I was deeply involved with a telecommunications project which aimed at predicting problems and recommend solutions with ADSL residential gateways. Most intriguingly I was at the helm of developing a user level interactive interface for Expertmaker's big data processing framework.

Internship at Content and Customisation