Senior ML Engineer (Telecom/Banking)
At a glance
Senior Machine Learning Engineering role at SSC HR Solutions. Remote, Egypt · full-time.
Pay not stated ML Engineer salary
remoteroles summary, based on the employer's posting.
What you'll do
- Build and operate production scores for churn, propensity, lifetime value, spend intent and response, from model training through monitoring
- Use customer data to create tabular predictive models that support customer scoring and prediction
- Run models through deployment, retraining, evaluation and calibration in a self-managed data platform
- Work with commercial stakeholders to connect predictions to the decisions they support
What you bring
- You have applied machine learning experience with models operating in production, beyond research or proof-of-concept work
- You bring deep hands-on skill in tabular prediction using customer data
- You have built churn or propensity models in telecom, banking, retail or another listed sector
- You have worked with model registries, version control, retraining, monitoring and drift detection
Who this fits
This senior role suits an engineer focused on production machine learning and customer scoring rather than research prototypes. The position is remote and based in Cairo, Egypt.
From the employer
Description
Owns the predictive customer scores that ship with the product: churn, propensity, lifetime value, spend intent, and response scoring, from training through to monitoring. Applies machine learning and tabular predictive modelling to customer data, building and managing production models that support customer prediction and scoring. Works across the full model lifecycle, including model training, deployment, retraining, monitoring, evaluation, and calibration within a self-managed data platform environment. Supports predictive use cases such as churn, propensity, lifetime value, spend intent, and response scoring, with a focus on models running in production.
Requirements
Requirements
- Applied machine learning with models running in production, not research or proof of concept.
- Deep hands on with tabular predictive modelling on customer data.
- Has built churn or propensity models in telco, banking, or retail.
- Training, deployment, and retraining pipelines in a self managed environment.
- MLOps practice: model registry, versioning, retraining, monitoring, and drift detection.
- Comfortable working inside a data platform rather than a notebook.
- Uplift or causal modelling for incremental targeting.
- Feature store design.
- Working with commercial stakeholders on what a prediction is used for.