Data Engineer, Personalization and Recommendations at eBay Classifieds Group

Posted on: 09/09/2021

Location: Amsterdam (ON-SITE)

full time

Crunchbase | Original Source

Tags: gcp flink spark apache openstack azure redis scala ml python aws docker elasticsearch kafka

[eBay Classifieds Group (eCG)]( is now part of Adevinta, an innovative leader in digital marketplaces spanning 17 countries. We’re all about matchmaking, and our sites help people find whatever they’re looking for in their local communities. Every connection made or item found makes a difference by creating a world where people share more and waste less. As a global network of loved local brands, including Marktplaats in the Netherlands, in Germany and leboncoin in France, our team of over 6,000 employees are there to make things better, safer and easier for the people who choose to visit and use our marketplaces every month. And we do that by being experts in our field, basing improvements on data and bringing together our network of talented teams. **About the team** The eCG central data product teams innovate and build products ranging from personalized, complementary and similar listings recommendation systems, to search ranking models, to user profiling and segmentation services, to performance statistics engines, to AdTech and others to offer our end users and partners to create perfect matches on our marketplaces. The marketplaces in the eCG portfolio fuel the central data platform with rich behavioral, content and user data on which we rely to build global services. The Personalization and Recommendations team is one of these teams with a mission to enable our marketplaces to improve the buying experience by better understanding our users and surfacing more relevant and inspirational content. With the Adevinta merge, we have more than 1 billion users across 17 countries and 4 continents. Currently we serve our recommendations to many markets and we try to make our recommendations as relevant as possible, and to do that we need to pick from millions of ads on our platform just a few that will be the best match for a user. It is a high-load environment with deep machine learning integration. We use different models to make decisions fast and precisely, and our goal is to create an ultimate recommendation that will take into account user’s preferences and intents, and inspire them to use our platforms in a more extensive way not only as buyers but also as sellers. We are on the lookout for top-notch software engineers to join our team and make a global impact in an exciting and dynamic environment. Come and join us! **About the role** As an engineer in thePersonalization and Recommendationsteam, you will build and run production-grade data and machine learning pipelines and products at scale in an agile setup. You will work closely with our data scientists, engineers, architects and product managers to create the technology that generates and transforms data into applications, insights and experiences for our users. We expect you to contribute to the architecture of our system, and help to make it more scalable and resilient. As part of our team, we want you to spot opportunities to improve the development work in all areas from coding and processes, to tools and testing. **Who are you** We are looking for someone who is passionate about data and machine learning. You have a strong focus on execution, delivery and customer impact and craft code that is understandable, simple and clean. You are a manager of one and a sharp communicator who can explain complex problems in clear and concise language. You have a growth-oriented mindset and a desire to teach, improve, and otherwise force multiply the strengths of the engineers that surround you. You are a fast learner and thrive on learning new technologies and don't believe in one-size-fits-all solutions. You are a great teammate and believe that you can achieve more on a team - that the whole is greater than the sum of its parts. * You have experience designing and productionizing large-scale distributed systems built around machine-learned models and big data. Experience with ML Ops and associated best practices. * You have strong expertise in Java and/or Scala programming languages. Python experience is a plus. * You have experience with batch and streaming technologies: e.g Apache Flink, Apache Spark, Apache Beam, Google DataFlow. * You have expertise with distributed data stores (Casandra, Google BigTable, Redis, ClickHouse, Elasticsearch) and messaging systems (Kafka, Google PubSub) at scale. * You have experience with Linux, Docker, private and/or public cloud (OpenStack, GCP, AWS, Azure). What we offer * Meaningful work with diverse, international, highly skilled and passionate product and tech teams across geographies which give you the chance to make a difference in our customers’ lives at a global scale. * International career opportunities throughout Adevinta. * Competitive compensation, conference & education budget. We value your personal and professional development. * A healthy work-life balance, i.e. part-time work, additional paid parental leave time, flexible working hours including working from home options. * A great atmosphere, open-minded company culture with several social team activities (online and offline). **Benefits** Benefits are an essential part of your total compensation for the work you do every day. Whether you’re single, in a growing family, or nearing retirement, Adevinta offers a variety of comprehensive and competitive benefit programs to meet your needs. Covid-19 People are the heart of Adevinta, and their health and well-being are our first priority. We continue to monitor local government guidance and partner closely with medical advisors to determine the safest and best next steps for everyone. As a result, most teams are working remotely, with a few teams able to collaborate in person with enhanced safety procedures. We will discuss the particular case for your region during the interview process. As a general rule, interviews will be completed remotely over video calls.