Software Engineer (Java/Python + Machine Learning)

Hi! Get to know the possibilities of cooperating with Scalo!

At Scalo, we focus on delivering software projects and supporting our partners in developing their business. We create software that enables people to make changes, act faster, and achieve better results. We utilize a wide spectrum of IT services to support our clients in achieving their business goals.

Our areas of activity include, among others:

• technology consulting,
• software development,
• embedded systems,
• cloud solutions,
• data management,
• dedicated project teams.

What do we offer as part of our cooperation?

• the opportunity to provide services in diverse projects from the Software, Embedded, Data, and Cloud Services areas,
• involvement in additional pre-sales and expert initiatives,
• access to medical care, a sports card, and a cafeteria platform in accordance with the applicable cooperation rules.

Daily tasks

• participation in a project from the e-commerce industry,
• designing, developing, and maintaining backend applications and solutions in Java, using Python in the area of data processing and Machine Learning model development,
• creating high-quality, readable, and efficient code ready for deployment to production environments,
• developing and implementing predictive models based on supervised learning, used in business solutions for the e-commerce industry,
• preparing, processing, and analyzing large tabular datasets using Pandas and NumPy libraries,
• building, training, and optimizing regression models, particularly using Gradient Boosting algorithms (e.g., LightGBM) and scikit-learn,
• designing and implementing the Feature Engineering process, including preparing features for predictive models and time series data,
• designing and conducting model validation, taking into account the specifics of temporal data, selecting appropriate metrics, and assessing the quality and stability of predictions,
• comparing model results with baseline solutions and identifying and eliminating problems related to overfitting, data leakage, and inconsistency in data processing between the training and production environments,
• integrating Machine Learning models with Java-based backend applications and ensuring their correct operation in the production environment,
• collaborating on the design and development of solution architectures that enable efficient sharing and utilization of ML models by business applications,
• participating in code review, testing, performance optimization, and maintenance of the developed solutions,
• collaborating with an international project team, data analysts, and other technical specialists to deliver solutions that meet business needs.

Requirements

• minimum 4 years of commercial experience in a similar role,
• very good knowledge of Java,
• practical knowledge of Python,
• experience in creating clean, readable, and efficient code ready for deployment to production environments,
• good knowledge of Machine Learning topics, particularly supervised learning,
• practical experience in building predictive models on tabular data, especially regression models,
• knowledge of Gradient Boosting algorithms and practical experience working with the LightGBM library,
• experience in preparing, processing, and analyzing large datasets using Pandas and NumPy libraries,
• practical knowledge of scikit-learn and/or LightGBM libraries in terms of building, training, and evaluating Machine Learning models,
• knowledge of Feature Engineering topics, including preparing features for predictive models,
• ability to design model validation, taking into account the characteristics of temporal data and selecting appropriate evaluation metrics,
• ability to compare model results with a baseline model and identify problems such as overfitting and data leakage,
• awareness of the importance of consistency in data processing and feature calculation between the training and production environments,
• ability to integrate Machine Learning models with Java-based applications,
• English language proficiency at C1 level, enabling free communication in an international project environment.

Nice to have:

• practical knowledge of Quantile Regression,
• experience in Time Series Feature Engineering,
• knowledge of SQL,
• experience with AWS services, particularly S3 and Athena,
• knowledge of Docker and Kubernetes,
• experience working with CI/CD processes,
• knowledge of monitoring tools, particularly Prometheus,
• experience with Machine Learning solutions used in production environments.

Must have: Java, Python, Machine Learning, LightGBM, scikit-learn, pandas, NumPy, Feature Engineering, Time series

Nice to have: SQL, AWS, AWS S3, Athena, Docker, Kubernetes, CI/CD, Prometheus