Samsara is looking to optimize and transform its global supply chain by designing, developing, and deploying advanced machine learning and statistical models to solve complex problems with direct business impact, such as forecasting demand and modeling supply risk.
Requirements
- Expertise in statistical modeling or machine learning, including time series forecasting, optimization, and anomaly detection.
- Strong coding skills in Python and fluency in SQL; experience developing and deploying production ML systems.
- Familiarity with MLOps practices, including automated testing, CI/CD, model versioning, and monitoring.
- Demonstrated track record building real-time inference pipelines and managing GPU/TPU resources.
- Familiarity with data visualization tools (e.g., Tableau, Power BI) and cloud platforms (e.g., AWS, GCP, or Azure).
- Able to design and validate experiments (A/B, multi-armed bandits) and apply Bayesian methods for uncertainty quantification.
- Proven track record building advanced forecasting models (e.g., Prophet, LSTMs, Transformer-based) for intermittent demand and seasonal patterns.
Responsibilities
- Own the design, training, validation, and deployment of ML and statistical models. (e.g., demand forecasting, inventory optimization, supplier risk scoring), ensuring robust MLOps practices and measurable ROI.
- Build predictive models to forecast demand, lead times, and cellular spend across Samsara’s global supply network.
- Create novel features using large-scale ERP, IoT, and third-party datasets; build pipelines and ETL jobs to serve models and stakeholders.
- Deliver production-grade code that supports both batch and real-time inference with MLOps best practices.
- Drive enhancements to our data infrastructure and analytics platform to support real-time model training, monitoring, and inference at scale.
- Establish governance frameworks, documentation standards, and quality controls for model development, validation, and lifecycle management.
- Mentor junior scientists through code reviews and collaborative project work.
Other
- 8+ years of experience in applied data science or machine learning, ideally in supply chain, operations research, logistics, or manufacturing.
- Master’s or PhD in Computer Science, Statistics, Data Science, EE, OR, or a related technical field.
- A passion for operational excellence, cost efficiency, and building scalable, data-driven solutions.
- Exceptional problem-solving, critical thinking, and communication abilities.
- This role is open to candidates residing in the US except the San Francisco Bay Metro Area, NYC Metro Area, and Washington, D.C. Metro Area.
