Big Data and Machine Learning Engineert
Introduced machine learning and NLP to the company and took over the big data projects attached to existing products.
Advocated and researched NLP systems, including topic modeling and sentiment analysis, to solved a range of business problems.
Developed an ETL pipeline for machine learning models on AWS using Step Functions which automated preprocessing of data on a (temporary) EMR Spark cluster and, training and deployment of API endpoints using Sagemaker.
Designed and developed automated news feed crawler using only AWS Lambda functions (and SNS + SQS services).
Researched and developed an automatic content extraction algorithm} achieving state-of-the-art results.
Deployed an Apache Airflow application running in a Docker container on an EC2 instance using Docker Machine.
Augmented the Spark (Scala) reporting pipeline to improve its efficiency and robustness.
Cheif Technical Officer
Founder and CTO of a music inducstry startup based in Sydney and Berlin