Principal Data Scientist

Lead the design, development, and deployment of high‑fidelity digital twin models for semiconductor fab operations, enabling accurate representation of WIP flow, equipment behavior, capacity constraints, and factory dynamics. Develop advanced discrete‑event, agent‑based, or hybrid simulation frameworks to analyze cycle time, throughput, bottlenecks, and scheduling scenarios across complex manufacturing systems. Drive AI‑ and ML‑enhanced simulation methodologies, including predictive modeling, prescriptive analytics, reinforcement learning, and optimization algorithms to improve factory performance and decision‑making. Collaborate closely with Operations, Industrial Engineering, Manufacturing, and Data Science teams to translate operational challenges into simulation experiments and data‑driven solutions. Build and maintain scalable simulation architectures that integrate real fab data (MES/EWS, equipment logs, sensor/IoT data) for continuous model calibration and accuracy improvement. Develop scenario analysis and “what‑if” studies to support capacity planning, equipment purchase decisions, technology transitions, dispatching strategy evaluation, and cycle‑time reduction initiatives. Lead the creation of predictive and prescriptive decision-support systems, combining simulation, optimization, and machine learning to enhance scheduling, resource allocation, and operational agility. Own end‑to‑end model validation and verification, ensuring technical robustness, traceability, and alignment with fab behavior and factory physics. Partner with IT/OT teams to operationalize digital twin models, integrating simulation capability into production environments and enabling real-time or near‑real‑time decision intelligence. Mentor and guide junior engineers and data scientists, fostering technical excellence and best practices across modeling, simulation, and advanced analytics. Communicate insights, model results, and recommendations to technical and non‑technical stakeholders through clear reports, presentations, and dashboards. - Bachelor's or Master's degree in Industrial Engineering, Systems Engineering, Computer Science, Electrical Engineering, or a related field. - PhD in a relevant discipline is a plus (e.g., Operations Research, Simulation Modeling, Digital Twin, Applied AI/ML). - Strong foundation in semiconductor manufacturing systems, factory physics, and production planning concepts. - Solid understanding of discrete‑event simulation (DES), agent‑based modeling, or hybrid simulation approaches. - Knowledge of statistics, optimization, and applied machine learning. - 5~12+ years of experience in semiconductor fab operations, digital twin development, or manufacturing optimization roles. - Hands-on experience building digital twin models for complex production systems (preferably 300mm/200mm fabs). - Proven track record designing or implementing: . Discrete-event simulation models for cycle time, WIP behavior, bottleneck analysis, or capacity planning. . AI/ML-based optimization (dispatching, scheduling, predictive modeling, anomaly detection). - Experience working with EWS/MES systems, fab scheduling/dispatching rules, and lot/equipment behavior. - Demonstrated collaboration with cross-functional teams (Ops, IE, Manufacturing Engineering, Data Science). - Experience deploying solutions into production IT/OT environments is a strong advantage. 1.Simulation & Modeling - Expertise in tools like AnyLogic, FlexSim, Simio, Plant Simulation, Arena, or custom Python-based simulation frameworks. - Capability to build scalable, data-driven, and object-oriented fab digital twin architectures. - Knowledge of factory physics, queueing theory, throughput modeling, and bottleneck analysis. 2. AI, Optimization & Analytics . ML/AI: scikit‑learn, TensorFlow/PyTorch (optional) . Optimization: OR‑Tools, Pyomo, Gurobi/CPLEX . Data processing: pandas, NumPy, SQL - Familiarity with reinforcement learning, heuristic optimization, or hybrid AI‑simulation methods. - Ability to design predictive models, prescriptive analytics, and real-time optimization algorithms 3. - Strong analytical mindset with the ability to simplify complex system behavior. - Excellent communication skills for explaining models, assumptions, and results to non-technical stakeholders. - Ability to lead technical initiatives, mentor junior engineers, and drive cross-functional collaboration. - Proactive problem-solving approach and ownership mindset.