Senior Machine Learning Engineer

About Checkmate

Checkmate is a restaurant technology solution provider that has continually evolved over time. We started in 2017 by integrating 3rd party platforms to the POS systems of restaurants. We have since then continually evolved to add multiple products to our portfolio, the primary ones being first party ordering solutions like web and app ordering, kiosks and catering. We have now recently moved into three new exciting products: Digital Menu Boards, Phone Ordering AI and Drive thru AI. We form a very core part of the restaurant technology ecosystem, and are continually adding more and more digital solutions for the restaurant brands to increase their sales. As you can see, this is a company that continually evolves and adapts and today we are powering digital ordering solutions for some of the largest brands in the world.

About the Role

We’re seeking a Senior-Level Machine Learning Engineer to join our growing Data Science & Engineering team. In this role, you will design, develop, and deploy ML models that power our cutting-edge technologies like voice ordering, prediction algorithms and customer-facing analytics. You’ll collaborate closely with data engineers, backend engineers, and product managers to take models from prototyping through to production, continuously improving accuracy, scalability, and maintainability.

Essential Job Functions

• Model Development: Design and build next-generation ML models using advanced tools like PyTorch, Gemini, and Amazon SageMaker - primarily on Google Cloud or AWS platforms.
• Feature Engineering: Build robust feature pipelines; extract, clean, and transform large-scale transactional and behavioral data. Engineer features like time-based attributes, aggregated order metrics, categorical encodings (LabelEncoder, frequency encoding).
• Experimentation & Evaluation: Define metrics, run A/B tests, conduct cross-validation, and analyze model performance to guide iterative improvements. Train and tune regression models (XGBoost, LightGBM, scikit-learn, TensorFlow/Keras) to minimize MAE/RMSE and maximize R².
• Own the entire modeling lifecycle end-to-end, including feature creation, model development, testing, experimentation, monitoring, explainability, and model maintenance.
• Monitoring & Maintenance: Implement logging, monitoring, and alerting for model drift and data-quality issues; schedule retraining workflows.
• Collaboration & Mentorship: Collaborate closely with data science, engineering, and product teams to define, explore, and implement solutions to open-ended problems that advance the capabilities and applications of Checkmate, mentor junior engineers on best practices in ML engineering.
• Documentation & Communication: Produce clear documentation of model architecture, data schemas, and operational procedures; present findings to technical and non-technical stakeholders.