Real-Time AI/ML Engineer for Industrial Manufacturing

Galatek; Singapore; Hybrid; SGD 90,000 - 130,000; Full time

Job summary

Galatek in Singapore is seeking an AI/ML Engineer (Industrial / Manufacturing) to design and deploy core machine learning models that enable autonomous parameter self-adjustment, real-time error compensation, and yield correlation across semiconductor manufacturing lines.

You will build real-time, low-latency ML solutions, deploy on edge compute nodes, and collaborate with Control Systems, Vision/Metrology, and Software Architecture teams to translate equipment dynamics into scalable AI models.

Responsibilities

• Autonomous Process AI: Design and implement real-time, closed-loop machine learning algorithms ("self-driving" recipes) that dynamically adjust process parameters in real time without manual operator intervention.
• Dynamic Error Compensation: Develop data-driven predictive models (e.g., Gaussian processes, neural networks, or reinforcement learning) to compensate for thermal drift, stage micro-vibrations, and parasitic motion errors on the fly.
• Yield & Defect Data Correlation: Build end-to-end data analytics and ML pipelines that correlate granular defect data across AOI, overlay metrology, and inline processing equipment sensor feeds to automatically identify root causes and yield limiters.
• Model Deployment & Inference: Deploy light-weight, low-latency ML models into edge compute nodes and high-performance communication architectures for real-time sub-millisecond execution.
• Cross-Functional Integration: Collaborate closely with Control Systems Engineers, Vision/Metrology Specialists, and Software Architects to translate physical equipment dynamics into scalable AI models.

Job description

Galatek in Singapore is seeking an AI/ML Engineer (Industrial / Manufacturing) to design and deploy core machine learning models that enable autonomous parameter self-adjustment, real-time error compensation, and yield correlation across semiconductor manufacturing lines.

You will build real-time, low-latency ML solutions, deploy on edge compute nodes, and collaborate with Control Systems, Vision/Metrology, and Software Architecture teams to translate equipment dynamics into scalable AI models.