4Bell Technology

Job Description

What You'll Do
 • Forecast demand across many short, sparse, intermittent series, and quantify the uncertainty.
 • Build optimization and sequential decision models that turn forecasts into actions: order quantity and timing, inventory policy, and supplier and substitution choices under budget, contract, pack-size, and leadtime constraints.
• Map supplier line items to a normalized catalog, with review workflows for uncertain matches.
• Detect anomalies and fraud in pricing, spend, invoicing, and supplier behavior, and surface what merits human attention.
• Use market basket and affinity analysis to learn what customers buy together and what they are likely to need next.
• Expose models as versioned, documented tools that agents and services can call, with calibrated confidence and predictable behavior on unexpected input
• Own model quality in production: baselines, backtesting that respects time and entity structure, error analysis, regression checks, and the call on when to retrain or roll back. Our platform team provides the monitoring and deployment machinery.
 • Design experiments and causal analyses that establish whether a decision model changed the outcome, and communicate findings and limitations to executives.
• Partner with Data Engineering on pipelines, Product Management on what is worth building, and AI Engineers on how your models get consumed.
What You'll Bring Required
• Carried ideas from open question to production in a small, autonomous group, often as the first or only person on the problem: framing it, building it, measuring honestly, and knowing when to stop.
• 8+ years in Data Science, Machine Learning, or Operations Research.
 • At least one model shipped to real users and measurably improved after launch.
• Forecasting, including sparse and intermittent series.
• Optimization and sequential decision problems under uncertainty: mathematical programming, heuristics, simulation, or dynamic programming.