Software Engineer - Forecasting & Scheduling

1w1 week ago

Assembled

San Francisco, US · Full-time · $135,000 – $280,000

About this role

Assembled is the unified platform orchestrating human agents and AI at scale for customer support. Companies like Canva, Etsy, and Robinhood use it to coordinate in-house agents, BPOs, and AI in one operating system. Backed by $71M from NEA, Emergence Capital, and Stripe, it enables faster service and smarter staffing.

You'll develop forecasting interfaces, data pipelines, and inference servers to predict support contact volume. This determines the optimal number of support agents required for specific days and times. Accurate predictions balance human and AI capacity effectively.

Design interfaces to collect team preferences and business constraints like labor laws. Create optimal schedules for thousands of support agents using forecasts and constraints. Tackle challenges similar to the nurse scheduling problem.

Enhance MLOps for efficient machine learning operations and rapid model deployment. Join with experience on ML or algorithmic teams using Python libraries like pandas, SciPy, and seaborn. Passion for statistical and runtime performance is key.

We encourage applications from great candidates even if not every requirement matches. Assembled values diverse perspectives and builds an inclusive workplace where everyone belongs and does their best work.

Requirements

Experience using Python libraries like pandas, SciPy, and seaborn for statistical or predictive work
Previous experience working on a machine learning or algorithmic team
Strong commitment to advancing statistical and runtime performance for reliable forecasting and scheduling
Familiarity with time series forecasting techniques
Knowledge of workforce optimization problems like nurse scheduling
Experience with MLOps for model deployment

Responsibilities

Develop forecasting interfaces, data pipelines, and inference servers to predict support contact volume
Determine optimal number of support agents required for specific days and times
Design and implement interfaces to collect and store team preferences and customer business constraints like labor laws
Create optimal schedules for teams of thousands of support agents based on forecasts and constraints
Enhance machine learning efficiency and operations for rapid model deployment and iteration
Build statistical models for contact volume prediction
Implement optimization algorithms for agent scheduling