Senior ML Engineer
At a glance
Senior Machine Learning Engineering role at SSC HR Solutions. Remote, Egypt.
Pay not stated ML Engineer salary
remoteroles summary, based on the employer's posting.
What you'll do
- Build and deploy production ML models for telecom tasks such as churn, customer grouping and demand forecasts
- Prepare and analyze customer data, then create features for supervised and unsupervised models
- Use Python and SQL to develop models and process data from multiple sources
- Run MLOps workflows for model versions, releases, production checks and retraining
- Track model performance and drift, address issues, and refine models using production results
What you bring
- At least four years in machine learning, data science or a related field
- Telecommunications experience is essential, including building and deploying production models for telco problems
- Strong Python and SQL skills for customer data preparation, feature work and model development
- Practical experience managing models through versioning, deployment, monitoring and retraining, using MLflow or an equivalent platform
Who this fits
This senior role suits an engineer with hands-on telecom ML experience who can take models from development into production and maintain them. The role is remote and based in Cairo, Egypt.
From the employer
Job Description
We are looking for a Senior Machine Learning Engineer with strong experience in the Telecommunications (Telco) domain to design, develop, deploy, and maintain production-ready machine learning solutions.
The ideal candidate will have hands-on experience in ML model development, feature engineering, deployment, monitoring, and retraining, with a strong understanding of MLOps practices and the end-to-end machine learning lifecycle.
Key Responsibilities
- Develop and deploy production-grade machine learning models for Telco use cases.
- Build ML solutions for use cases such as customer churn prediction, customer segmentation/clustering, and demand forecasting.
- Prepare, clean, transform, and analyze large customer datasets.
- Perform feature engineering and develop relevant features for machine learning models.
- Train, validate, and evaluate supervised and unsupervised machine learning models.
- Use Python for data preparation, model development, validation, and automation.
- Use SQL to access, extract, transform, and process data from various sources.
- Implement and maintain MLOps pipelines across the ML lifecycle.
- Manage model versioning, deployment, production monitoring, and retraining.
- Monitor model performance and data/model drift in production and take appropriate corrective actions.
- Collaborate with data engineers, data scientists, and business stakeholders to deliver scalable ML solutions.
- Ensure ML models are reliable, maintainable, and suitable for production environments.
- Continuously improve existing models, features, and ML workflows based on production results.
Requirements
Requirements
- 4+ years of experience in Machine Learning, Data Science, or a related field.
- Telco/Telecommunications domain experience is a MUST.
- Proven experience building and deploying production ML models for Telco use cases, such as:
- Churn prediction
- Customer clustering/segmentation
- Demand forecasting
- Customer behavior prediction
- Strong knowledge of supervised and unsupervised machine learning techniques.
- Strong hands-on experience with Python for data preparation, feature engineering, and ML model development.
- Strong SQL skills for accessing, processing, and analyzing customer data.
- Hands-on experience with feature engineering and customer data preparation.
- Practical MLOps experience, including:
- Model versioning
- Model deployment
- Production monitoring
- Model retraining
- Experience with MLflow or an equivalent MLOps/model lifecycle management platform.
- Experience taking ML models from development through production deployment and ongoing monitoring.
- Ability to evaluate model performance and identify opportunities for model improvement.
- Strong understanding of the end-to-end machine learning lifecycle.
- Experience with Dataiku or equivalent enterprise ML platforms is a plus.
- Experience with Spark, Feature Stores, or uplift modelling is a plus.