Senior Machine Learning Engineer (MLOps)

Redwood Logistics is seeking a Senior Machine Learning Engineer to build and operate infrastructure that moves machine learning models from development into reliable production. The role owns the ML platform, including training pipelines, model serving, feature stores, monitoring, and model governance across logistics use cases.

Responsibilities:

• Design, build, and maintain the ML platform data scientists and ML engineers use to train, evaluate, version, and deploy models across the organization
• Develop and maintain model serving infrastructure supporting both real-time (low-latency REST APIs) and batch (large-scale scoring jobs) inference patterns
• Implement safe deployment patterns: canary releases, shadow mode evaluation, A/B testing infrastructure, and rollback mechanisms for production models
• Build comprehensive model monitoring systems that detect data drift, concept drift, prediction distribution shifts, and degradation in business outcomes
• Partner closely with data scientists to understand model requirements, reduce friction to production, and build tooling that gives them leverage
• Work with Product and Engineering to integrate model predictions into product features and operational workflows reliably and at scale
• Identify new opportunities to drive business impact through data exploration and collaboration with key stakeholders
• Own the feature store: design feature pipelines, manage feature definitions, ensure consistency between training and serving environments, and reduce feature engineering duplication across teams
• Collaborate with cross-functional teams, including software engineers, data scientists, business stakeholders, and product teams, to gather inputs and assumptions and understand business processes along the way

Requirements:

• MS or PhD in Computer Science, Data Science, Applied Mathematics, Physics, or equivalent work experience
• 5+ years of software or ML engineering experience, with 3+ years focused on MLOps, ML platform engineering, or ML infrastructure in a production environment
• Proven experience owning the end-to-end ML lifecycle in production: training, deployment, monitoring, and retraining at scale
• Strong Python engineering skills; production-grade, tested, maintainable code across ML and data pipelines
• Hands-on experience with at least one major ML platform (MLflow, SageMaker, Vertex AI, Databricks) and pipeline orchestration tool (Airflow, Prefect, Kubeflow)
• Solid understanding of machine learning fundamentals, enough to reason about model behavior, evaluation metrics, and the implications of drift
• Experience building CI/CD for ML: automated testing, staging environments, canary deployments, and rollback strategies for models
• Experience working with Data Warehouses and ETL pipelines (e.g., Redshift, Databricks, Snowflake, Airflow)
• Ability to communicate with technical and non-technical stakeholders is a plus
• Three years of experience in supply chain, logistics, transportation, or a similar space is a plus