Well look to you for:
Develop, deploy, and maintain Machine Learning models and retraining systems: Integrate data science models into Data and ML pipelines in collaboration with data scientists and data engineersDesign and execute machine learning tests and experiments, by applying best practices for experiment tracking and model registryBuild and orchestrate MLOps pipelines including CI/CD to automate data ingestion and transformation, model (re-)training,(re-)deployment, inference and monitorSupport the industrialization of scalable data science solutions through automation and continuous deliveryIdentifying changes in models and shifts in data distribution that could affect model performance, and apply appropriate measures for protecting against driftsApply strong testing and quality assurance practicesSupport field trials with our customers using the mobility analytics software modules and toolsAnalyses and checks the suitability of an algorithm if it caters the needs of the current task/business problemAttend meetings, submit work progress reports and perform related duties as required
All about you
We value passion and attitude over experience. Thats why we dont expect you to have every single skill. Instead, weve listed some that we think will help you succeed and grow in this role:
- Degree in computer science or engineering supplemented by extensive training in data science/ML or related disciplines
- Excellent knowledge of Python programming, with software engineering skills including DevOps and CI/CD pipelines
- Experience with Python data science stack (pandas, scikit-learn, keras, numpy, tensorflow)
- Experience in building supervised and unsupervised ML models and in optimizing model (hyper-)parameters tuning for performance and costs
- Strong mathematical skills (probability and statistics, algebra, optimization)
- Knowledge of continuous integration tools and technologies (Jenkins, Ansible, Git)
- Experience with SQL/NoSQL database management
- Experience with LINUX environment (shell scripting)
- Experience with cloud technologies, preferably on Azure
- Experience with containerization and orchestration tools (Docker, Airflow, NiFi, Kubernetes, OpenFaaS) for production
- Experience in MLOps frameworks (e.g. MLFlow and DVC)
- Experience in big data technologies (e.g. Spark, Hadoop, Apache Kafka etc.)
- Proficiency with web APIs development and design (e.g. REST)
- Experience in writing technical documentation
- Agiles procedures