Applied Scientists - AI Economics

Auger • Bellevue, WA

1d • Onsite

About The Position

Build at Auger Auger is the autonomous operating system for supply chains. It connects enterprise supply chain systems—ERP, WMS, TMS—into a single data layer, then uses AI to detect problems, evaluate trade-offs, and execute decisions automatically. The platform eliminates the coordination tax: the time and capital lost when disconnected systems force humans to become the integration layer between planning and execution. Actions that previously required days of meetings and manual coordination happen in seconds, within constraints the customer defines. Founded by Dave Clark and backed by $100M from Oak HC/FT. Headquartered in Bellevue, Washington. About the Role The AI Economics Team at Auger is building an AI and agentic-powered market intelligence system that enables our customers to forecast supply chain risk, optimize sourcing decisions, and respond to global disruptions in real time. We are looking for an Applied Scientist to design, deploy, and scale the systems at the core of this platform. You will own the end-to-end ML lifecycle for production systems including demand and cost forecasting models, supplier reliability prediction, NLP pipelines for news and document intelligence, and real-time cost calculation engines. Your work will directly inform sourcing recommendations that move billions of dollars in procurement spend. This role sits at the intersection of applied ML and economics research and production engineering. You will collaborate closely with economists on causal inference methodology, with data engineers on feature pipelines, and with product teams to translate model outputs into actionable customer-facing tools. You should be comfortable shipping models that run at scale, monitoring their performance in production, and iterating based on real-world feedback. Our current technical stack includes time-series forecasting (demand signals, commodity prices, delivery timing), causal ML for supplier effect estimation, NLP for document parsing and news sentiment (certificates of origin, compliance documents, global news feeds), and real-time scoring APIs serving predictions to interactive dashboards.

Requirements

• 4+ years experience building and deploying ML models in production environments
• Strong proficiency in Python and ML frameworks (scikit-learn, XGBoost/LightGBM, PyTorch)
• Experience with time-series forecasting methods (ARIMA, Prophet, gradient boosting, neural forecasters)
• Familiarity with NLP pipelines: text classification, named entity recognition, document parsing, or sentiment analysis
• Experience with Production ML infrastructure: model serving, feature stores, monitoring, retraining workflows, and deployment into existing CI/CD systems(including unit tests and integration tests)
• SQL proficiency
• Experience with data pipeline tools (Airflow, dbt, or similar)
• Ability to communicate model behavior and limitations to non-technical stakeholders

Responsibilities

• Own the end-to-end ML lifecycle for production systems including demand and cost forecasting models, supplier reliability prediction, NLP pipelines for news and document intelligence, and real-time cost calculation engines.
• Design, deploy, and scale the systems at the core of this platform.
• Collaborate closely with economists on causal inference methodology.
• Collaborate with data engineers on feature pipelines.
• Collaborate with product teams to translate model outputs into actionable customer-facing tools.
• Ship models that run at scale.
• Monitor model performance in production.
• Iterate based on real-world feedback.

What This Job Offers

• Job Type: Full-time
• Career Level: Senior
• Education Level: No Education Listed