Divergent Operations Analyst focused on manufacturing analytics to convert production data into operational insights and decision tools. Develops statistical and machine learning models for time and cost prediction and unifies factory data sources.
Responsibilities
Develop and validate statistical and ML models correlating process time, staffing, and engineering data to enable granular time and cost prediction; initial application in pricing, extending to simulation and factory scaling.
Unify equipment, MES, ERP/BOM, staffing, and engineering data into a cohesive data model that serves as a shared foundation for pricing, simulation, factory scaling, predictive models, and the team’s broader set of tools.
Define source mappings, metric definitions, and data quality rules, including anomaly detection to flag inconsistencies in data inputs (e.g., work orders); partner with the central Data, AI, and Software teams to operationalize data and software tools.
Identify operational inefficiencies and implement data-driven process improvements with operations and automation teams, validating data against shop floor conditions.
Lead cross-functional projects from discovery and requirements through prototyping, business case and ROI justification, and implementation.
Conduct ad hoc and scenario analyses supporting pricing, capacity, staffing, and investment decisions.
Communicate and document data models, methodology, and assumptions for technical and non-technical stakeholders.
Qualification
Bachelor’s or Master’s in Data SciencePythonSQLApplied statistics and supervised MLGitMES/ERP data structures (work ordersEquipment data flowsDiscrete-event simulation (SimPyEngineering drawingsCost accounting
Required
Ability to lawfully access information and technology that is subject to US export controls
Bachelor’s or Master’s in Data Science, Statistics, CS, Operations Research, or related field (or equivalent experience)
Demonstrated experience in operations analytics, analytics engineering, data science, or data-intensive manufacturing roles
Hands-on experience with production data and shop floor execution in a manufacturing environment, including work orders, BOMs, routings, and production scheduling
Python: pandas, NumPy, scikit-learn, statsmodels, matplotlib/Plotly; data extraction, API integration, task automation
SQL: complex joins, window functions, CTEs; relational data modeling; cleaning and validation of high-volume operational and time-series data
Applied statistics and supervised ML: hypothesis testing, regression, classification, tree-based ensembles; feature engineering, cross-validation, model evaluation; anomaly detection for input data validation
Manufacturing operational metrics (cycle time, yield, throughput, utilization, OEE, WIP)
Git; documented, reproducible code
Integration of AI tools into daily workflow
Independent project ownership and management: scoping, requirements gathering, timelines, dependencies, and stakeholder alignment without prescriptive direction
Translation of ambiguous business problems into structured problem statements and analytical approaches
Preferred
Microsoft Fabric or equivalent lakehouse platforms (Databricks, Snowflake): navigation and data extraction
MES/ERP data structures (work orders, routings, BOMs, genealogy, NCRs)
Equipment data flows, IIoT protocols, and time-series data (OPC‐UA, MTConnect, MQTT, historians)
Discrete-event simulation (SimPy, AnyLogic) and optimization methods (LP/MIP, OR-Tools)
Additive manufacturing and metal process chains (LPBF, heat treatment, CNC machining, CMM/CT inspection)
Engineering drawings, GD&T, and CAD
Cost accounting, pricing, and financial modeling (unit economics, margin, ROI)
Lean and continuous improvement methods (Six Sigma, DMAIC, process mapping) and shop floor change management
