Machine Learning Engineer

Oredata Yazılım Anonim Şirketi; Fatih; Presencial; TRY 350.000 - 550.000; Jornada completa

Descripción de la vacante

Oredata Yazılım Anonim Şirketi ищет старшего инженера ML для разработки масштабных решений в авиационной индустрии. Требуется опыт работы с Python и традиционным ML, Spark/PySpark и выводом моделей в продакшн. Уделяется внимание данным и инфраструктуре для реального применения моделей.

Кандидат будет разрабатывать функции, обучать и валидировать модели, обеспечивать мониторинг и повторное обучение, сотрудничать с командами Data Engineering и Platform в окружении OpenShift.

Formación

• Сильный практический опыт Python и традиционного ML.
• Умение работать с Scikit-learn, XGBoost, LightGBM.
• Опыт работы с Apache Spark / PySpark для обработки больших данных.
• Опыт вывода моделей в продакшн и MLOps-практики.

Responsabilidades

• Проектирование, разработка и оптимизация ML-моделей для бизнес-задач.
• Построение и внедрение решений для сегментации клиентов, рекомендаций и прогнозирования.
• Работа с большими данными через Spark/PySpark, извлечение данных из хранилищ и баз.
• Разработка и поддержка кода, мониторинг и автоматизированное повторное обучение.

Conocimientos

Python

Machine Learning

Problem-solving

Team collaboration

Educación

Bachelor's or Master’s in CS/Math/EE

Herramientas

Scikit-learn

XGBoost

LightGBM

Apache Spark / PySpark

Spark MLlib

OpenShift

S3 / Iceberg / Feature Store

Descripción del empleo

Описание:

Ready to take your Machine Learning expertise to new heights? We are looking for an experienced Senior Machine Learning Engineer to contribute to large-scale Machine Learning and AI projects within the aviation industry. The ideal candidate will have strong expertise in traditional Machine Learning, hands-on experience with Apache Spark/PySpark, and a proven track record of developing and preparing ML models for production environments. The role will focus entirely on developing Machine Learning solutions for business use cases such as Customer Segmentation, Recommendation Systems, Revenue Forecasting, and Demand Prediction, utilizing our existing technology and data infrastructure.

Задачи:

• Design, develop, and optimize Machine Learning models to address complex business challenges.
• Develop and implement ML solutions for Customer Segmentation, Recommendation Systems, and Forecasting.
• Work with large-scale datasets using Apache Spark and PySpark, extracting data from both cloud-based storages and relational databases.
• Perform feature engineering, model training, validation, evaluation, and hyperparameter optimization.
• Develop clean, scalable, and production-ready Machine Learning code.
• Write robust code to support model monitoring and automated retraining processes.
• Evaluate and continuously improve model performance.
• Collaborate with Data Engineering and Platform teams to deploy and integrate ML solutions into the existing OpenShift environment (No new platform design/infrastructure setup is required).

Требования:

• Strong hands-on experience in Python and traditional Machine Learning.
• Proficiency in ML libraries such as Scikit-learn, XGBoost, and LightGBM.
• Hands-on experience with Apache Spark / PySpark for large-scale data processing and Machine Learning.
• Solid understanding of supervised and unsupervised learning techniques, including Classification, Regression, and Clustering.
• Practical experience in at least one of the following areas: Customer Segmentation, Recommendation Systems, or Forecasting.
• Experience in feature engineering, model development, evaluation, and optimization.
• Experience developing production-ready ML models and code.
• Ability to develop code supporting model monitoring and automated retraining pipelines.
• Strong SQL skills and experience working with relational databases (e.g., Teradata, Oracle).
• Strong analytical thinking and problem-solving skills.
• Experience with Spark MLlib.
• Familiarity working within OpenShift or container-based environments.
• Experience working with S3, Apache Iceberg format, and Feature Store architectures.
• Experience with ML lifecycle management and MLOps practices.
• Experience delivering large-scale Machine Learning solutions in production environments.