Rivian is looking to enhance the efficiency, resilience, and intelligence of its supply chain by developing, deploying, and maintaining ML-powered solutions.
Requirements
- Strong programming proficiency in Python.
- Experience with machine learning frameworks/libraries such as scikit-learn, TensorFlow, PyTorch.
- Solid understanding of relational databases (SQL) and experience with big data technologies (e.g., Spark, Hadoop, Snowflake, Databricks).
- MLOps Platforms: Hands-on experience building production ML systems using tools like MLflow, Kubeflow, Vertex AI, or SageMaker for experiment tracking, model registry, and serving.
- Familiarity with cloud platforms (Databricks, AWS, Azure, GCP) and their relevant services for ML and data.
- Experience with DevOps principles and tools (e.g., Docker, Kubernetes, CI/CD pipelines like Jenkins, GitLab CI, GitHub Actions) for infrastructure as code and automated deployments.
- Experience with Infrastructure as Code tools (e.g., Terraform, Databricks DABs) is highly desirable.
Responsibilities
- Design and Develop ML Models: Collaborate with stakeholders to understand supply chain challenges and design, develop, and implement machine learning models (e.g., forecasting, optimization, anomaly detection, predictive maintenance) to address them.
- Data Preparation & Feature Engineering: Work with large, complex datasets from various sources, performing data cleaning, transformation, and feature engineering to prepare data for model training and deployment.
- Model Deployment & MLOps: Design, build, and maintain robust MLOps pipelines to effectively deploy, monitor, and manage machine learning models in production environments. This includes setting up automated model retraining, versioning, and performance tracking.
- Data Pipeline Development: Contribute to the development and optimization of scalable data pipelines to ingest, process, and store supply chain data, ensuring data quality and accessibility for ML applications.
- CI/CD for Machine Learning: Design, implement, and maintain CI/CD/CT (Continuous Integration/Continuous Delivery/Continuous Training) pipelines to automate the testing, validation, and deployment of models and the underlying infrastructure.
- Advanced Monitoring & Observability: Implement comprehensive monitoring solutions for both model performance (accuracy, drift, bias) and operational health (latency, throughput, error rates, cost).
- Infrastructure as Code (IaC): Build and manage scalable ML infrastructure on cloud platforms using IaC principles and tools (e.g., Terraform, Databricks DABs).
Other
- 3-5 years of practical experience in machine learning engineering, data science, or data engineering roles.
- Solid understanding of statistical modeling, machine learning algorithms, and experimental design.
- Basic understanding of data warehousing concepts, ETL processes, and data governance.
- Excellent analytical and problem-solving skills with a keen eye for detail.
- Genuine interest in supply chain operations and the automotive industry, particularly electric vehicles.
