Senior Data​/Machine Learning Engineer

Job Description

Summary:

Digital products play a central role in how we create value for customers, support the teams who serve them, and shape the consumer experience.  ​Our product organization brings together small, empowered teams that move with clarity, speed,  and purpose, enabling digital to be a meaningful source of advantage across Coca-Cola’s North America Operating Unit. Our work spans customer journeys, service delivery, sales workflows, and the platforms that connect them.

We are raising our standards for product craft and rebuilding the systems behind these experiences. As a Tech Lead specializing in Machine Learning and Data Engineering, you will lead the technical direction for end-to-end ML capabilities that ship as part of our product, while also ensuring the data foundations (events, pipelines, feature tables, and governance) are reliable and scalable. You’ll partner with Product, Design, Data Science/Analytics, and platform teams to frame problems, define success metrics, and guide solutions from data modeling and feature engineering through model training, deployment, monitoring, and iteration.

This is a hands-on leadership role for engineers who can set standards, unblock teams, and drive execution across the ML and data stack without formal people-management responsibilities. What You Will Work On:  Build ML-powered data products that model transaction drivers and surface optimized actions as insights to be embedded within integrated internal and external digital experiences that shape how our beverage brands activate across retail, food service, and digital channels.

The success of our products is tied directly to measurable transaction lift at the point of sale, a primary objective of the North America Operating Unit and The Coca-Cola Company as a whole. How We Work You’ll be part of a dedicated, cross-functional team (Product, Design, Engineering) that is:
Empowered to solve problems, not just build features Accountable for outcomes, not output Collaborative by default, from discovery through delivery Continuously learning, using data and customer insight to improve

Key Responsibilities Technical direction for a product ML domain: problem framing, approach selection, evaluation strategy, and iteration Data and feature foundations: event/telemetry definitions, transformation logic, feature/label tables, and training/serving consistency Production ML systems: deployment patterns (batch/online), model performance/latency tradeoffs, and operational readiness Quality and reliability: data quality checks, model monitoring (drift/performance), alerting, and runbooks Engineering standards: design reviews, code review quality, documentation, and reusable patterns for ML + data workflows Mentorship and enablement: coaching engineers through complex work and unblocking delivery across teams Develop, Train & Evaluate Models Build baselines and iterate on model approaches appropriate to the product problem (e.g., gradient boosting, deep learning, ranking) Lead feature engineering with strong data discipline: define entities and joins, validate labels, and ensure training/serving consistency Run experiments and evaluate models using sound methodology (train/validation splits, cross-validation as appropriate, error analysis) Document findings and recommendations clearly for technical and non-technical audiences Deploy & Operate Models in Production Deploy models to production (batch and/or real-time) with attention to latency, reliability, and cost Implement monitoring for upstream data and feature freshness/quality, drift, and model performance;

define alerting and response playbooks Automate repeatable training and evaluation workflows (versioning, reproducibility, and…