Job Description

Opportunity Maersk, the world\'s largest shipping company responsible for moving 20 % of global trade, is on a mission to become the Global Integrator of Container Logistics. To achieve this, we are transforming into an industrial digital giant by combining our assets across air, land, ocean, and ports with our growing portfolio of digital assets to connect and simplify our customer\'s supply chain through global end-to-end solutions, all the while rethinking the way we engage with customers and partners. In this role as Lead ML Engineer on the Global Data and Analytics (GDA) team, you will be working on our new strategic visibility initiative to develop recommendation solutions facing internal and external users. The overall objective is to develop actionable recommendations which enable unprecedented flexibility and unlock new types of services for our internal users and our customers. Building on top of a best-in-class visibility data foundation, you will be partnering with product managers and engineering counterparts to develop scalable solutions following industry best-practices. You will be empowered to take ownership of your domain and we expect you to proactively contribute to identifying opportunities and solutions. You should have demonstrated ability to make sense out of large, integrated datasets, and build statistical and machine learning (ML) models on top of these data sets. Hands-on experience developing recommendation systems and putting solutions to production in collaboration with data engineering and software engineering is crucial for this role. No prior knowledge of logistics needed we will help you learn what you\'ll need to succeed. Key responsibilities Develop, test, and deploy \'recommender\' system solutions and other analytical tools together with the team. In addition to the topics mentioned above, this can range from building integrated data sets over analyses to dashboards and machine learning models Lead model development end-to-end incl. MLOps (mindset and technical implementation). Specifically, you will drive problem formulation, modeling approach, implementation, testing and monitoring. Collaborate with software engineers and data engineers to deploy recommendation solutions to production Partner with product managers to drive maturation of ideas into production solutions, including challenging problem formulation Communicate effectively with technical and non-technical audiences Key Skills: Retrieval & Ranking: Expertise in design of retrieval and ranking techniques for Online and Offline environments to recommend \'choices of actions\' to customers that will have a high likelihood to convert Embeddings & retrieval: Core expertise in embeddings combined with Nearest neighbour index implementation to identify top candidates for \'choices of actions\' [based on historical features] Filtering: Core expertise in filtering & retrieval models [such as matrix factorization or two tower linear models etc..] to generate a list of (multiple) candidates for the \'choices of action\' Soring & Ordering: Core expertise in design of Scoring models that feeds into a ordering stage to align the output of the recommendation to the constraints of the situation/customer/other parameters, which then starts a feedback loop Expertise in not just model development, but designing a \'recommender system\' that serves the recommendations in production Basic qualifications BSc/MSc/PhD in computer science, data science or related discipline with 12+ years of industry experience building cloud-based ML solutions for production 8+ years of hands-on experience with Python and SQL, incl knowledge of common python data science libraries Hands-on experience building end-to-end data products based on recommendation technologies Experience with collaborative development workflow: version control (we use github), code reviews, DevOps (incl automated testing), CI/CD Team player, eager to collaborate Preferred qualifications Experience with a common dashboarding technology (we use D3Js, PowerBI) Experience working in cross-functional product engineering teams following agile development methodologies (scrum/Kanban/ ) Experience with Spark and distributed computing Hands-on experience with MLOps solutions, including open source solutions. Experience with containerization: Kubernetes & Docker

foundit