Staff Data Scientist, Global Operations Intelligence, SMAI

Key Responsibilities

Capacity Optimization & Advanced Analytics

Develop optimization models to improve factory capacity utilization, throughput, cycle time, tool loading, and bottleneck management.

Build mathematical models for capacity planning, production allocation, constraint identification, and investment prioritization.

Apply operations research techniques such as linear programming, mixed-integer programming, constraint programming, stochastic optimization, and simulation-based optimization.

Design algorithms to support factory maxout strategies and identify opportunities to unlock additional capacity without unnecessary capital investment.

Semiconductor Manufacturing Problem Solving

Partner with manufacturing, industrial engineering, planning, equipment, process, and business teams to understand capacity constraints and operational challenges.

Analyze tool capability, process flows, product mix, WIP movement, cycle time, dispatching rules, and factory constraints to recommend optimization opportunities.

Support scenario analysis for capacity expansion, product mix changes, technology transitions, and capital planning decisions.

Develop data-driven recommendations that improve decision quality across tactical and strategic planning horizons.

Data Science, AI/ML & Decision Intelligence

Build predictive and prescriptive analytics models using large-scale manufacturing and planning datasets.

Apply machine learning techniques to forecast capacity demand, identify abnormal patterns, predict bottlenecks, and recommend operational actions.

Integrate optimization engines with data pipelines, visualization dashboards, and decision-support tools.

Collaborate with software engineering teams to deploy scalable analytical models into production systems.

Stakeholder Engagement & Business Impact

Translate complex analytical findings into clear, actionable insights for technical teams and business leaders.

Quantify business impact in terms of capacity gain, cost avoidance, cycle time reduction, productivity improvement, and capital efficiency.

Drive cross-functional alignment by communicating assumptions, model logic, trade-offs, and recommendations effectively.

Contribute to roadmap development for advanced capacity intelligence, factory digital twin, and AI-driven planning capabilities.

Required Qualifications

Master’s degree or higher in Operations Research, Industrial Engineering, Data Science, Computer Science, Applied Mathematics, Statistics, Systems Engineering, or a related quantitative field.

Strong experience in mathematical optimization, simulation, statistical modeling, or machine learning.

Proficiency in programming languages such as Python, R, or similar analytical programming tools.

Experience with optimization libraries or solvers such as Gurobi, CPLEX, OR-Tools, Pyomo, PuLP, or equivalent.

Strong capability in data analysis, feature engineering, model validation, and algorithm design.

Experience working with large datasets from manufacturing, supply chain, planning, or operational systems.

Ability to structure ambiguous business problems into analytical frameworks and deliver practical solutions.

Strong communication skills with the ability to explain complex models to both technical and non-technical stakeholders.

Demonstrated ability to work cross-functionally in a fast-paced, global, and matrixed environment.

Preferred Qualifications

PhD in Operations Research, Industrial Engineering, Applied Mathematics, Systems Engineering, or a closely related field.

Strong semiconductor manufacturing experience, particularly in wafer fabrication, assembly/test, advanced packaging, capacity planning, or industrial engineering.

Deep understanding of semiconductor manufacturing concepts such as process flows, tool groups, WIP, cycle time, bottlenecks, dispatching, product mix, yield, and equipment utilization.

Experience developing capacity planning, production scheduling, factory simulation, or digital twin solutions.

Hands-on experience with discrete-event simulation, agent-based simulation, or factory simulation platforms.

Experience deploying optimization or AI/ML models into production environments.

Familiarity with manufacturing systems such as MES, ERP, APS, data warehouses, or planning platforms.

Knowledge of cloud platforms, data engineering pipelines, APIs, and scalable model deployment is a plus.

Experience leading analytical projects from problem definition through implementation and business adoption.

Proven track record of delivering measurable business impact through optimization, automation, or AI-driven decision support.

Key Technical Skills

Mathematical optimization: LP, MILP, nonlinear optimization, constraint programming, stochastic optimization.

Simulation: discrete-event simulation, what-if analysis, scenario modeling, digital twin concepts.

Data science: regression, classification, clustering, time-series forecasting, anomaly detection, predictive modeling.

Programming: Python, SQL, R, Spark, Git.

Optimization tools: Gurobi, CPLEX, OR-Tools, Pyomo, PuLP.

Visualization and communication: Power BI, Tableau, Plotly, Dash, or equivalent.

Manufacturing analytics: capacity modeling, bottleneck analysis, tool utilization, cycle time, WIP flow, throughput modeling.

Core Competencies

Strong analytical and structured problem-solving mindset.

Ability to balance technical rigor with practical business implementation.

Excellent stakeholder management and communication skills.

Comfortable working with ambiguity and evolving business requirements.

Passion for applying AI, optimization, and advanced analytics to real-world manufacturing challenges.

Strong ownership mindset with the ability to drive initiatives from concept to execution.

Collaborative style with the ability to influence across engineering, operations, planning, and leadership teams.