Senior Machine Learning Engineer (Fraud)
J
JobgetherFraud Detection
Remote-first work environment available across eligible Canadian provinces.Full-TimeSenior
SalaryCompetitive annual base salary range of approximately $153,000 to $213,000 CAD
Apply NowOpens the employer's application page
Job Details
- Experience
- 6+ years
- Required Skills
- PythonKubeflowMachine LearningMLFlowPyTorchAirflowSpark
Requirements
- 6+ years of experience researching, training, tuning, and launching machine learning models at scale.
- Proven experience delivering high-impact machine learning models in low-latency production environments.
- Strong Python programming skills with experience writing production-quality, maintainable code.
- Experience building and evaluating models for tabular classification problems, including approaches such as LightGBM, XGBoost, CatBoost, or similar technologies.
- Experience with deep learning frameworks, preferably PyTorch.
- Experience working with distributed data processing or parallel computing frameworks such as Spark, Ray, Dask, or equivalent tools.
- Experience with ML lifecycle tooling for experimentation, training orchestration, and model monitoring, such as Kubeflow, Airflow, MLflow, or similar platforms.
- Ability to use AI-powered developer tools to accelerate development, debugging, experimentation, and code quality.
- Strong understanding of designing solutions that integrate across multiple software components.
- Ability to work effectively within large codebases and provide constructive engineering feedback.
- Excellent written and verbal communication skills for collaboration with global technical teams.
Responsibilities
- Develop and improve machine learning models for fraud prediction using tabular, graph, and behavioral data.
- Build and maintain scalable feature pipelines and training datasets using internal and external data sources.
- Prototype new modeling approaches, conduct offline experiments, and transition successful solutions into production.
- Integrate machine learning models into batch and real-time decision systems while improving reliability, latency, and scalability.
- Monitor model performance, data quality, and system health to ensure continued effectiveness as fraud patterns evolve.
- Define and improve model retraining, backtesting, and monitoring workflows.
- Identify and implement foundational improvements to machine learning development processes and infrastructure.
- Partner with engineering, fraud analytics, product, and ML platform teams to define requirements and evaluate technical trade-offs.
- Communicate technical findings, model performance, and recommendations clearly to both technical and non-technical stakeholders.
- Contribute to code quality through testing, documentation, debugging, and peer code reviews.
View Full Description & ApplyYou'll be redirected to the employer's site
