Senior Machine Learning Engineer (Python, MLOps, GCP, Vertex AI)

About the role

UPS Technology's Machine Learning Engineering teams build intelligent systems that power its Smart Logistics Network, optimize UPS Airlines and support global transportation operations. This Senior Machine Learning Engineer role covers the full ML lifecycle, from data exploration and feature engineering to model training, evaluation, deployment and monitoring, while helping shape MLOps practices and mentoring junior engineers.

Key responsibilities

• Design, deploy and maintain production-ready ML models and pipelines for real-world applications.
• Build and scale ML pipelines with Vertex AI Pipelines, Kubeflow and Airflow, and manage infrastructure as code with Terraform and Helm.
• Implement automated retraining, drift detection and redeployment of models.
• Develop CI/CD workflows (GitHub Actions, GitLab CI, Jenkins) tailored for ML.
• Implement model monitoring, observability and alerting on accuracy, latency and cost.
• Integrate feature stores, knowledge graphs and vector databases for advanced ML and RAG use cases.
• Ensure pipelines are secure, compliant and cost-optimized, and drive MLOps best practices including reproducibility, versioning and lineage tracking.
• Mentor junior engineers and contribute to the ML platform architecture and technical roadmap.

Required profile

• Bachelor's or Master's degree in Computer Science, Engineering, Mathematics or a related field (PhD is a plus).
• 5+ years of experience in machine learning engineering, MLOps or large-scale AI/data science systems.
• Strong foundation in data structures, algorithms and distributed systems.
• Hands-on experience building and deploying ML models at scale in cloud environments.

Required skills

• Python (scikit-learn, PyTorch, TensorFlow, XGBoost) and SQL.
• Containerization (Docker, Kubernetes) and orchestration (Airflow, TFX, Kubeflow).
• CI/CD pipelines and infrastructure as code (Terraform, Helm).
• Big data and streaming (Spark, Flink, Kafka, Hive, Hadoop).
• Model observability tools (Prometheus, Grafana, EvidentlyAI) and governance (WatsonX).
• Preferred: real-time inference, feature stores, model interpretability (SHAP, LIME, Fairlearn), and domain experience in logistics or supply chain.