Skip to main content

Assembled

Software Engineer - Forecasting & Scheduling

United States (Remote)$135k–$280kfulltimemidAdded 1 month ago

About this role

Join Assembled to build forecasting and scheduling systems that predict support contact volume and optimize agent staffing across thousands of support team members. You'll develop ML-powered interfaces and data pipelines while enhancing MLOps to support rapid model deployment.

What you'll do

  • Develop forecasting interfaces and data pipelines to predict support contact volume and required agent capacity
  • Design scheduling systems to create optimal agent schedules based on forecasts, preferences, and business constraints
  • Build inference servers for model deployment and real-time predictions
  • Enhance MLOps infrastructure to support rapid model iteration and deployment
  • Collect and manage team preferences and customer business constraints for scheduling
  • Optimize both statistical and runtime performance of forecasting and scheduling systems

What they're looking for

  • Python (pandas, SciPy, seaborn)
  • Machine learning and predictive modeling
  • Data pipeline development
  • MLOps and model deployment
  • Statistical analysis
  • Algorithmic problem-solving
  • Software engineering best practices
  • Performance optimization
Apply with Autofill

Opens the application — the Jobs AI extension fills it for you. Set up autofill

Opens the official application on the employer’s site. No login required.

Assembled

Assembled builds AI-driven customer support software with forecasting, scheduling, and workforce optimization capabilities designed to predict support volume and optimize agent staffing at scale. The company is hiring Software Engineers to develop its design system, frontend product experiences, ML-powered interfaces, and AI-enhanced workflows across engineering and design teams.

View all jobs at Assembled

Likely interview questions

  • Walk us through your experience building forecasting models. What libraries and statistical approaches have you used, and how did you evaluate model performance?
  • Describe a time you worked on an optimization problem with constraints (like the nurse scheduling problem). What was your approach and what challenges did you face?