Role Purpose: 

The Data Engineer II will play a crucial role in enhancing Jumio's data infrastructure and analytics capabilities. This role is vital for building and maintaining data transformation pipelines, monitoring data distribution shifts, managing dataset versions, and analyzing system performance. Your contributions will support the continuous improvement of Jumio's machine learning models, ensuring they operate with high accuracy and efficiency in various production environments.

Role Value: 

As a Data Engineer II at Jumio, you will be instrumental in advancing our data engineering processes and infrastructure. Your expertise in building data pipelines, managing datasets, and analyzing system performance will directly impact the efficiency and reliability of our machine learning models. By automating data transformation processes and monitoring data distribution shifts, you will help ensure that our models are frequently updated and operate effectively in production.

T-Shaped Engineering Expectation:

In addition to your deep expertise in data engineering, you will bring a broad understanding of software development, testing, and data science. As a T-shaped Data Engineer, you will take full ownership of the data infrastructure you build, ensuring it is reliable, thoroughly tested, and capable of supporting our machine learning and analytics efforts. Your skills in Python, SQL, and cloud environments will enable you to tackle complex data challenges, provide valuable insights into system behavior, and contribute to Jumio's mission to deliver top-tier identity verification solutions. Your work will play a critical role in maintaining our leadership in the online identity verification, eKYC, and AML solutions market

Example Responsibilities

• Building data transformation pipelines with humans in the loop: in order to increase the frequency of our ML models updates, you will be in charge of automating and expanding a semi-manual datasets generation pipeline, including tagging jobs preparation, scheduling and post-processing.
• Data distribution shift monitoring: you will design a system capable of detecting changes in our data distribution, as well as the apparition of unknown data types by monitoring the behavior of our ML models in production
• Dataset growth strategy: you will use your developed expertise of our business data and system monitoring tooling to help identify valuable zones of expansion of our automated solution
• Datasets versioning management: you will be in charge of managing and documenting datasets versions of an ecosystem of highly dependent and changing datasets
• Data volatility management: you will help develop solutions to stabilize our datasets in an environment where data retention is time-limited
• System performance analysis: you will support your team and the organization in answering questions related to the behavior of our automated system on particular transactions and data buckets by diving into the data and our models. You will use your advanced Python skills to produce targeted performance metrics that will lead you from a metric to problematic examples 

Experience and Qualifications 

• Building data pipelines in dynamic and changing environments
• Wrangling data with Python (pandas, numpy) and SQL
• Performing data analysis and data deep dives using Jupyter notebooks (or other notebook tools)
• Experience and/or interest in Machine Learning and Data Science
• Proficiently leveraging cloud environments

Great to have Experience and Qualifications 

• Familiarity with privacy by design
• Serverless data engineering 
• Java, Apache Spark / Flink

@Work 
Our newest office, Jumio is in Prestige Tech Park III and growing fast. A hub of technical excellence with Machine Learning enablement at its core, the engineers and team are committed to learning and innovation. They set the bar high.