We are looking for a Senior Machine Learning Engineer to help build the intelligence behind OMS+ IA. The focus is models that make a measurable difference inside enterprise order management: product and cross-sell recommendations, churn and propensity scoring, demand and delivery forecasting, and document intelligence. The role is split between product and delivery. On the product side, you will help design and build the models that ship as part of the platform. On the delivery side, you will work directly with customer data and customer teams to get those models performing in real environments, where the data is messier and the requirements are more specific than any roadmap anticipates.
Key Responsibilities
- Design, train, and evaluate models for prediction, ranking, and recommendation problems in order management. Things like cross-sell recommendations, churn and propensity scoring, and demand forecasting.
- Contribute across the modeling lifecycle: problem framing, data preparation, feature engineering, training, evaluation, and retraining strategy.
- Work with product management to translate roadmap priorities into well-framed modeling problems.
- Support delivery engagements: profile customer data, tune and validate models against it, and work with implementation and solution engineering teams to get results the customer can trust.
- Help build reproducible training pipelines and experiment tracking in Python so results can be reviewed, rerun, and defended.
- Profile, clean, and validate large-scale enterprise SAP data, and be candid about what the data can and cannot support.
- Package models and pipelines for deployment.
- Define the production monitoring a model requires (drift detection, performance regression signals, data quality checks).
- Act as the modeling counterpart to IT when production looks wrong, translating between model behavior and operational reality.
- Help integrate model output into the product stack through clean, well-documented service interfaces.
- Apply responsible AI practices: bias evaluation, explainability, and careful data handling.
- Document models and explain behavior, limitations, and trade-offs to engineers, delivery teams, sales, and customers alike.
- Review peers' modeling work and help raise team standards for rigor and reproducibility.
Required Qualifications
- Demonstrated depth in applied machine learning and data science, with models you built that reached production and were measured there.
- Strong Python skills and fluency with the modern ML ecosystem: PyTorch or TensorFlow, scikit-learn, pandas, and NumPy.
- A solid statistics foundation: experimental design, appropriate evaluation metrics, and the judgment to tell a real result from a lucky one.
- Strong SQL and comfort working with large relational datasets.
- Experience building data and feature pipelines that run on a schedule and survive contact with messy source systems.
- Experience handing work to a separate operations or platform team: packaging, documenting, and specifying what a model needs to run well.
- Comfort working directly with customers and delivery teams.
- TypeScript or JavaScript proficiency sufficient to integrate cleanly with our product stack.
- Clear written and verbal communication.
You should be able to explain a model to a salesperson and a trade-off to an architect in the same afternoon.
- Bachelor's degree in Computer Science, Statistics, Mathematics, Engineering, or a related technical field, or equivalent practical experience.
Preferred Qualifications
- Working knowledge of Kubernetes and containerized deployment.
- MLOps tooling experience such as MLflow, Kubeflow, Weights & Biases, Airflow, or Dagster.
- LLM and agentic workflow experience: retrieval-augmented generation, fine-tuning, evaluation harnesses, and vector databases.
- Recommender systems or time series forecasting at production scale.
- Exposure to SAP data structures (SD, MM) or other enterprise ERP data models.
- Experience in a customer-facing implementation, delivery, or professional services capacity.
- Cloud platform experience (AWS, Azure, or GCP) and SAP HANA Cloud ML libraries (PAL/APL).
- Graduate degree in machine learning, statistics, or a closely related field.
Ready to apply? Please upload your resume in English.
DataXstream Inc., is an equal-opportunity workplace and an affirmative-action employer. We are always committed to equal employment opportunities regardless of race, color, ancestry, religion, sex, national origin, sexual orientation, age, citizenship, marital status, disability, gender identity, or Veteran status. Discrimination is not welcome on the basis of any other status protected by the laws or regulations in the locations where we work.
New Zealand