About the job
The Staff Engineer in Analytics and AI/ML for Digital Manufacturing is dedicated to advancing data-driven manufacturing within our supply chain operations. This role involves leading the design, development, and implementation of analytics and artificial intelligence/machine learning solutions that provide both diagnostic and predictive insights to support real-time performance management and informed decision-making in intelligent, compliant operations.
Responsibilities
Define technical requirements and architecture for analytics and AI/ML solutions across manufacturing environments (edge, OT, and cloud). Lead end-to-end delivery of analytics and ML solutions, including data ingestion, feature engineering, model development, validation, deployment, and lifecycle management. Design, implement, and operate production-grade pipelines and inference (batch and real time), with monitoring and SLAs for latency, availability, and throughput. Translate manufacturing challenges (yield, downtime, quality, throughput) into measurable use cases with clear KPIs and expected ROI. Establish MLOps and governance practices (model versioning, experiment tracking, reproducibility, access control, audit trails) aligned to regulated manufacturing expectations (CSV, GxP where applicable). Partner with Manufacturing Engineering, Operations, Quality, IT, and R&D to prioritize and scale high-value use cases (predictive quality, anomaly detection, predictive maintenance, process optimization) and translate them into scalable analytics; ensure adoption through documentation, playbooks, training, and stakeholder engagement. Apply statistical methods and experimentation (e.g., DOE, SPC, capability analysis) to quantify drivers, validate improvements, and support continuous improvement.
Qualifications
Minimum
Bachelor’s or Master’s degree in Computer Science, Data Science, Statistics, Engineering, or a related quantitative field. 7+ years of experience delivering analytics and/or ML solutions in production environments (manufacturing, supply chain, healthcare/MedTech, or other regulated industries preferred). Proven track record delivering ML/AI solutions into production at scale; experience in manufacturing or industrial/OT environments strongly preferred. Experience with manufacturing and industrial data sources (e.g., MES, OPC UA, PLC logs, telemetry, sensors) and translating domain requirements into deployable ML solutions. Strong Python skills; experience with ML libraries (e.g., scikit-learn, TensorFlow, PyTorch) and data processing frameworks (e.g., Spark/PySpark). Hands-on MLOps experience, including orchestration, CI/CD, model serving, monitoring/observability, automated retraining, and experiment tracking (e.g., MLflow). Proficiency in SQL and data modeling; familiarity with lakehouse/data lake patterns (e.g., Delta) and cloud data services (AWS or Azure equivalents), including secure architecture design. Applied expertise in time-series and process analytics (anomaly detection, forecasting, classification/regression), including feature engineering and model interpretability/performance evaluation. Experience with model governance, validation, and compliance in regulated environments; familiarity with data governance, security, and role-based access controls (CSV/GxP where applicable). Strong communication and stakeholder-management skills, including the ability to document architecture/validation artifacts and present to technical and non-technical audiences.
Preferred
Experience with cloud analytics and lakehouse platforms and orchestration (e.g., Databricks, Spark/Delta) and effective collaboration with data engineering teams. Familiarity with digital manufacturing architectures and standards (e.g., ISA-95/ISA-88); unified naming/semantic standards are a plus. Experience with visualization and decision-support tools (e.g., Power BI, Tableau) and building role-appropriate dashboards.