Machine Learning Engineer @ VirtusLab

What we expect in general:

• The ability to work in hybrid model from Krakow office is a must (1 day per week).
• Hands-on experience in deploying Python projects.
• Strong experience in writing high-quality Python code.
• Experience with orchestration tools such as Airflow.
• Knowledge of Spark or other distributed data processing tools.
• Experience with Kubernetes ecosystem as a user.
• Strong experience in Azure and Docker
• Ability to work in a team and participate in the design process.
• Good command of English (B2/C1).
• Strong communicator
• Team player with mentoring ability
• Proactive and responsible
• Strategic thinker with big-picture perspective

Project Scope

We provide price optimisation solutions in close collaboration with a major UK retailer’s data science team. Together, we build projects to enable quick exploration and productionisation of the ML models and respective optimisation algorithms in a hybrid-cloud environment. The end goal is to provide APIs for the optimiser to solve pricing class problems across multiple business domains.

Tech Stack

Python (pySpark, Airflow, Azure SDK), Spark K8S cluster, Azure ML and IaC with Terraform, CI/CD with GitHub Actions, Docker

Challenges

There are many pricing problems in the global retailer world which share similar structures and constraints. We focus on building robust solutions that are reusable across multiple domains, leveraging a hybrid on-prem and cloud infrastructure, and ensuring top quality while maintaining quick iterations.

Team

The core engineering team consists of 5-6 talented people in Poland. We collaborate closely with the client’s product management and data science team.

A few perks of being with us

• Building tech community
• Flexible hybrid work model
• Home office reimbursement
• Language lessons
• MyBenefit points
• Private healthcare
• Training PackageVirtusity / in-house training
• And a lot more!

,[Implementation of the end-to-end Machine Learning Lifecycle, starting from data preparation over experimentation to continuous monitoring of data and models in production, PySpark data pipelines to load and transform large amounts of data to produce smaller, significant features used in modelling and analytics., Provisioning all cloud resources that support the model development in AzureML with IaC using Terraform., The selection of the best architectural patterns to solve business problems., Building robust and maintainable code in the cloud and on-prem to bring models fast and reliably to production., Establishing a mature DevOps culture and working on solutions that are reusable in multiple business domains.] Requirements: Python, Airflow, Spark, Data processing tools, Kubernetes, Azure, Docker, Communication skills Additionally: Building tech community, Flexible hybrid work model, Home office reimbursement, Language lessons, MyBenefit points, Training Package, Virtusity / in-house training.

Kategorie

artificialIntelligence

Odpovědět na inzerát