Data Engineer / Machine Learning Developer
PressReader (http://www.about.pressreader.com) is the world’s leader in published media distribution, offering the largest digital library of daily press hosting over 7,000 newspapers and magazines from over 100 countries and distributing them on millions of computers, tablets and mobile devices in every market.
Offering the world’s most engaging reading experience to millions of readers in 60 languages, PressReader can be found in leading libraries, hotels, airlines, corporate and government offices, cruise ships, airport lounges, schools and restaurants around the world.
We work with publishing houses of all types and sizes, including The New York Times, The Globe and Mail, The Guardian, The Irish Times, Cosmopolitan, Stuff and T3 . The company has two operational entities in Vancouver, Canada (PressReader) and in Dublin, Ireland (PressReader International).
As part of our international expansion, we have an immediate opening for a Data Engineer / Machine Learning Developer, based in our new Dublin offices, to take our data pipeline and targeting/personalization engine to the next level.
- Design and optimize data processing architecture
- Develop and maintain machine learning models for personalization, recommendation engine and targeting
- Write production-ready code in Python and/or Scala
- Proactively monitor event data and present findings to the team to help drive product decisions
- Solid background in Mathematics, Statistics and Machine Learning
- Knowledge of Hadoop ecosystem and similar ETL based frameworks
- Experience in building data pipelines using Apache Spark, AWS EMR, AWS Data Pipeline or similar technologies
- Knowledge of machine learning theory and algorithms: SVM, random forest, gradient-boosting methods etc.
- Scala or other common data pipeline languages etc.
- Proficiency with Python and common machine learning libraries
- Experience with streaming event systems like Kafka, AWS Kinesis
- Experience with NoSQL databases such as Cassandra, MongoDB, AWS DynamoDB
- Good communication skills
- Work with minimal supervision, be proactive and self-motivated
- BS or MS in Computer Science or related field (Machine Learning, Data Mining, Natural Language Processing, Information Retrieval). PhD is a big plus.
- Experience building and maintaining real-time personalization/recommendation systems at scale
- Health Insurance
- Company Pension Scheme
- Gym Subsidy
- Training & Education Reimbursement Program