ML Data Engineer

Position: ML Data Engineer

Who We Are

Bakkt is a trusted digital asset platform that enables consumers to buy, sell, store, send and spend digital assets. Bakkt’s platform is available through the Bakkt App and to partners through the Bakkt platform. Bakkt was founded in 2018 with a unifying vision: to connect the digital economy. We power commerce by enabling consumers, businesses and institutions to unlock value from digital assets.

Since our inception, we have hit a number of milestones, working behind the scenes to build a platform worthy of our vision – lowering barriers of entry into cryptocurrency, launching partnerships with some of the world’s premier brands and adding value to consumers’ digital assets by making their rewards and loyalty programs more compelling.

Bakkt acts as a profound bridge connecting the digital ecosystem and sitting at the intersection of crypto, loyalty and payments. Our platform enables consumers to leverage their digital assets – from cryptocurrency, to select loyalty points, gift cards and merchant offers – in new and exciting ways. It also enables companies & merchants to access all these capabilities, extending engagement with their customers, creating moments of delight while broadening the appeal and daily use of their loyalty and rewards programs. Now, let’s get to the real reason why you’re here – how we can work together.

Responsibilities

As an ML Data Engineer, you will be responsible for innovation, design and implementation of modern data landscape. This involves establishing process, principles, design, implementation and management of enterprise data platforms, analytical platforms, AI/ML platforms, Martech platforms and Lakehouse platforms including building out data engineering delivery principles and standards involved. Engaging Product, Enterprise Architecture, and other Technology teams, evaluating architecture and solutions for all things data. Reporting to the leadership for Data Engineering and Data Platform, you will work closely with other team members like data architects and business analysts to understand what the business is trying to achieve, move data from source to target, and design optimal data models. You will be also responsible for building and maintaining the data platform. This hands-on technical role demands excellent knowledge and ability to demonstrate the best practices in the industry.

• Design, architect, implement and maintain data platforms that encompass the entire lifecycle of data in process, data in motion and data at rest in cloud environment such as Azure, AWS, and GCP (preferred)
• Build out customer data platform for martech domain that delivers marketing and personalization
• Create, monitor and maintain business critical integration services/ETL jobs such as order processing, notifications, report deliveries, invoicing, fraud reporting, and order updates
• Build data pipelines to ingest data from multiple sources, designing scalable, efficient, reliable and secure DWH, and data lakes
• Collaborate with Data Scientists, Product Owners and Software Developers to translate business requirements into analytics and machine learning algorithms
• Develop, train and test alternative machine learning algorithms for specific tasks and projects
• Assess performance and prediction accuracy of the models on the train and test datasets
• Integrate machine learning models with applications e.g. via new or existing end points
• Develop, integrate and maintain ML pipelines working closely with infra engineers
• Perform other duties as may be assigned by management and report progress proactively

Required Skills & Experience

• 4-8 years of data engineering and machine learning experience in an externally facing, high-transaction, high-volume business environment
• Hands-on experience with Python (preferred), R, M, Bash or equivalent languages
• Experience working with different data sources e.g. MS Cloud SQL, Postgress, MySQL, Snowflake, SharePoint, Json, GCP Buckets, REST APIs to name a few
• Experience with DAX and Mashup, date dimensions, measures, hierarchy and granularity
• Hands-on experience implementing models such as knn, decision trees, random forest, ann, ranknet, and learn to rank (preferred)
• Experience with martech/finance domain, search engine (Solr LTR) optimization and recommendation systems preferred
• Experience with eda, bi-variate and uni-variate analyses, imputations, histograms, box plots, scatter plots, heat-maps, and other visualization techniques (Python preferred)
• Experience with designing and implementing cloud based and SaaS data warehouse (e.g. BigQuery, SSAS Cubes, Snowflake) and developing ETL/ELT pipelines
• Experience working in a high-paced environment, being self-driven, and working independently

Please note that this is contract/contract to hire position and the candidate should be a US citizen or Green Card holder to apply.

Bakkt is devoted to having diversity in its workforce and is proud to be an equal opportunity employer. Bakkt does not make any employment decisions based on race, color, religion, sex, national origin, veteran status, disability, age, sexual orientation, gender identity of any other characteristic protected by law.