Senior Data Scientist, Software Engineering

Research, design, and implement advanced machine learning (ML) solutions, including image classification, time series and waveform-based models, for semiconductor manufacturing and related applications; Develop and optimize embedded software components that integrate ML algorithms into proprietary hardware systems, ensuring real-time performance and reliability; Architect and implement end-to-end MLOps pipelines, including data ingestion, preprocessing, model training, deployment, monitoring, and lifecycle management, leveraging cloud platforms and container orchestration technologies; Integrate labeling systems into the MLOps lifecycle (e.g., human-in-the-loop labeling, active learning, dataset curation tools) and design, implement, and operate reliable data stores for MLOps, including object storage, time-series databases, feature stores, and metadata registries, with robust data lineage, provenance tracking, governance, access control, and auditability; Build and maintain data pipelines for large-scale data processing, feature engineering, and model development, ensuring robustness and scalability across distributed environments; Design and develop web-based applications and services to deliver data visualization, configuration, and operational control of ML-driven solutions, integrating with backend servers and cloud infrastructure; Create and maintain automated processes and algorithms for data cleansing, anomaly detection, and interpretation of complex signals from manufacturing hardware; Collaborate with cross-functional teams to translate business and engineering requirements into actionable AIdriven solutions, including defining experiments, validation plans, and performance metrics; Develop software modules and visualization tools for interpreting machine and process signals, enabling actionable insights for R&D and production optimization; Implement CI/CD workflows for ML applications, ensuring seamless integration, version control, and automated deployment across environments; and Communicate technical findings and analytics insights to stakeholders, provide technical leadership and guidance to cross-functional teams, and serve as an internal expert on ML, MLOps, and software integration.

In order to perform the above-mentioned tasks, the following skills and experience are required: Experience designing and implementing ML-based solutions, including both image classification models and waveform-based ML models; Experience with Python for data science and ML development; Experience with embedded software programming with C++ and OOP, web application development, and databases; Experience integrating ML components into production environments, optimize performance, and ensure scalability across distributed systems; Experience with data preprocessing, feature engineering, and workflow automation for ML models; Experience with containerization (e.g., Docker, Podman) and orchestration tools (e.g., Kubernetes); Experience designing and implementing full-stack AI solutions, from embedded systems to cloud-based services, ensuring robust security and compliance; and Experience with Git, CI/CD pipelines, and automated deployment strategies for ML applications. Requires a Bachelor’s degree or foreign equivalent in Data Science, Computer Science or a closely related field, and at least two (2) years of experience in a Data Scientist, Software Engineer or related occupation. Option to work from home (hybrid) may be available. Please send C.V. to amcgrath@kns.com .