Engineering Lead - Machine Learning

Job Description

Description

The role

We are looking for a Machine Learning Engineering Lead to design and develop high-throughput ML services by building pipelines to ingest large and complex data sets , designing model serving solutions and deploying machine learning applications on a next-generation platform. One that is motivated to evolve our e-commerce platform, by defining its future, building a flexible and high-performant top-notch tech platform for machine learning-based services .

You will be working in a very friendly environment and be part of a well-motivated, multicultural, talented and growing team of Software Engineers, QAs, Data Scientists and Data Analysts, to help build and optimize our data-driven products, through research and experimentation in a big data context .

If you love to learn and expand your competencies in a data-driven philosophy, if you are willing to share knowledge and would love to be part of the building process to reach the top, using the latest technology stack and having fun doing it, this is an opportunity you can’t miss.

What you’ll do

• Lead engineers in a world-class machine learning team and partner with the Data Science Lead in order to solve challenging ranking problems in an e-commerce platform;
• Work with the team to set and maintain engineering standards and practices while motivating engineers to challenge the status quo, to grow and go far;
• Architect and build scalable & reliable data processing pipelines for machine learning-based services using state-of-the-art technologies ( e.g. Cassandra, Apache Beam, Apache Spark, and Hadoop ecosystem, Apache Kafka, Elasticsearch, MongoDB, etc. );
• Build, deploy, monitor and experiment machine learning-based applications and APIs;
• Constantly evolve data models & schema design of our online (interactive) and batch ranking platforms;

Who you are

• Display leadership and inspire others by example, acting as a role model in living and breathing the team and the organization values;
• A Python developer with a focus on data processing and orchestration, and machine learning frameworks and libraries (e.g., Pandas, Vaex, Dask, Scikit-learn, Gensim, PySpark, Airflow, Keras, TensorFlow, and PyTorch) but always open to eventually use other languages and platforms;
• Have worked with cloud-based data engineering platforms such as Google Cloud Platform ( e.g., Cloud Dataflow, Cloud Dataproc, Cloud Pub/Sub, etc.), Azure (e.g. Data Bricks, Data Factory, HDInsight, Stream Analytics, Data Lake Storage, etc. ) but not limited to them (not mandatory);
• Experienced in designing and running batch/stream data pipelines;
• Knowledgeable and proven experience in ML/Data Continuous Integration & Deployment platforms;
• Comfortable to deal with trade-offs involving latency, throughput, transactions;
• Acquainted of ML algorithms such as Logistic Regression, XGBoost or LSTMs;
• A person that stays on top of all the best practices of modern software and data engineering;
• You are a keen advocate of quality and continuous improvement;
• Someone who is autonomous and able to make important technical decisions that will have a positive impact on our platform;
• Someone interested in large-scale systems and passionate about solving complex problems;
• Not afraid of failing, because we challenge assumptions and push boundaries since we have a culture of experimentation and learning from our mistakes so that we continuously improve!
• Excellent communication skills. Speak/read/write English fluently.