AI & Digital Solutions Technologist

Are you looking to power the next leap in the exciting world of advanced electronics? Do you want to help solve problems that drive success in the rapidly evolving technology and connectivity landscape? Then bring your problem-solving, passion, and creativity to help us power the next leap in electronics.

At Qnity, we’re more than a global leader in materials and solutions for advanced electronics and high-tech industries – we’re a tight-knit team that is motivated by new possibilities, and always up for a challenge. All our dedicated teams contribute to making cutting-edge technology possible. We value forward-thinking challengers, boundary-pushers, and diverse perspectives across all our departments, because we know we play a critical role in the world enabling faster progress for all. Learn how you can start or jumpstart your career with us.

Key Responsibilities:

Applied Machine Learning & Statistical Analysis

• Formulate lab, process, inspection, and experimental problems as supervised, unsupervised, time-series, anomaly-detection, optimization, or decision-support tasks with clearly defined inputs, outputs, constraints, and success metrics.
• Build regression, classification, clustering, anomaly-detection, pattern-recognition, and sequential-learning models using formulation, process, inspection, analytical chemistry, metrology, image, video, and experimental outcome data.
• Prepare datasets through data extraction, cleaning, joins, filtering, missing-value handling, outlier review, labeling strategy, feature engineering, train/validation/test splitting, and leakage prevention.
• Evaluate model performance using appropriate statistical and ML metrics, cross-validation methods, error analysis, sensitivity checks, calibration review, and practical operating thresholds.
• Interpret model results using feature importance, SHAP or similar explainability methods, residual analysis, confusion matrices, root-cause review, and domain validation with lab specialists.
• Support formulation design, process prediction, candidate screening, performance trade-off analysis, experiment prioritization, active learning, and decision-support workflows when aligned with R&D needs.

Computer Vision, Video & SOP Intelligence

• Build or support image- and video-based workflows for defect detection, classification, segmentation, object detection, feature extraction, visual quality inspection, and process monitoring.
• Apply computer vision, VLM, or video-understanding methods to improve SOP compliance, procedural traceability, deviation detection, retrospective video search, and operator guidance.
• Support camera, sensor, lighting, labeling, validation, and workflow-integration activities needed for reliable lab inspection and monitoring use cases.
• Evaluate model robustness, false-alarm behavior, visual context limitations, and practical operating requirements before routine lab use.

Workflow Enablement, Deployment & Digital Tools

• Convert model outputs into usable dashboards, alerts, reports, batch-scoring scripts, inference pipelines, APIs, decision-support tools, and user-facing prototypes for lab users.
• Partner with data engineering and IT teams to access source data, connect SQL or NoSQL databases, manage run logging, support traceability, and enable controlled deployment in laboratory workflows.
• Develop reproducible analysis packages using structured code, notebooks, version control, environment documentation, model artifacts, experiment tracking, and validation records.
• Define monitoring needs for deployed models, including input data drift, performance drift, failure modes, retraining triggers, model ownership, and user feedback loops.
• Support cloud, database, edge AI, containerization, or application-prototyping approaches where needed to improve workflow reliability, maintainability, scalability, and adoption.

Generative AI & R&D Knowledge Workflows

• Evaluate and apply LLM, VLM, retrieval-augmented generation, embeddings, instruction workflows, and knowledge-assistant concepts to support R&D knowledge access and lab decision-making.
• Develop approaches to search technical documents, summarize experiments, extract structured information, compare prior studies, and support SOP or troubleshooting knowledge workflows.
• Assess model quality, retrieval relevance, hallucination risk, data security, and usability before recommending use in laboratory or R&D workflows.
• Collaborate with stakeholders to define practical AI use cases that reduce manual effort, improve information reuse, and accelerate experimental learning.

Lab Automation & Cross-Functional Collaboration

• Support selected lab automation opportunities by identifying repetitive SOP steps, manual handling pain points, inspection needs, or monitoring gaps that may benefit from ML, CV, robotics, or semi-automated assistance.
• Assist with automation feasibility evaluation, camera or sensor integration, localization, monitoring, workflow validation, and data collection needed to support robust digital or automated solutions.
• Work closely with R&D, lab operations, process specialists, engineers, technicians, data engineering, and IT to understand user needs and deploy solutions in practical lab settings.

• Communicate results, limitations, implementation requirements, and recommended next steps clearly to both technical and non-technical stakeholders.

Required Qualifications:

• Bachelor’s or master’s degree in Data Science, Computer Science, Statistics, Engineering, Materials Science, Chemistry, Chemical Engineering, or a related technical discipline, or equivalent relevant experience.
• Hands-on experience applying machine learning, statistical analysis, or computer vision to laboratory, industrial, process, experimental, inspection, or R&D data.
• Strong Python coding capability, including pandas, NumPy, scipy, scikit-learn, visualization libraries, data preparation, feature engineering, model training, model evaluation, and reproducible analysis.
• Practical understanding of supervised learning, unsupervised learning, anomaly detection, model validation, cross-validation, error analysis, overfitting control, data leakage prevention, and metric selection.
• Experience with common ML, deep learning, or CV libraries such as PyTorch, TensorFlow, OpenCV, Hugging Face, or similar tools.
• Ability to translate lab or process problems into structured data science tasks, define practical success metrics, evaluate model limitations, and communicate findings clearly to technical and non-technical stakeholders.
• Working knowledge of data quality control, labeling strategy, experiment tracking, model documentation, validation practices, deployment considerations, and basic database concepts.
• Effective collaboration and communication skills for working across R&D, lab operations, process specialists, data engineering, IT, and internal client teams.

Preferred Qualifications:

• Master’s degree with relevant experience in data science, AI/ML, industrial analytics, scientific computing, materials informatics, or applied R&D analytics.
• Practical computer vision experience for image inspection, defect detection, segmentation, classification, measurement, monitoring, or video analytics workflows.
• Experience with formulation design, materials discovery, molecular design, chemical process optimization, sequential learning, active learning, or experimental R&D decision support.
• Experience with LLMs, VLMs, video foundation models, retrieval-augmented generation, embeddings, knowledge-assistant applications, or multimodal AI workflows.
• Familiarity with Azure, SQL, MongoDB, vector databases, Hugging Face, LangChain, Docker, TensorRT, Triton, edge AI deployment, or similar tools for integration and deployment.
• Experience with lab automation, wet-process handling, robotic arms, collaborative robots, ROS / ROS 2, vendor SDKs, camera integration, or hand-eye calibration.
• Prior experience in electroplating, surface finishing, PCB, advanced packaging, semiconductor wet-process labs, advanced manufacturing labs, or industrial R&D environments.

Join our Talent Community to stay connected with us!

Qnity is an equal opportunity employer. Qualified applicants will be considered without regard to race, color, religion, creed, sex, sexual orientation, gender identity, marital status, national origin, age, veteran status, disability or any other protected class. If you need a reasonable accommodation to search or apply for a position, please visit our Accessibility Page for Contact Information.

Qnity offers a comprehensive pay and benefits package. To learn more visit the Compensation and Benefits page.

We use Artificial Intelligence (AI) to enhance our recruitment process.