SMTS, Battery Manufacturing Quality Engineer (Data & Imaging)

QuantumScape Corporation•San Jose, CA

23d•$112,500 - $163,200•Onsite

About The Position

QuantumScape is seeking a highly motivated engineer for the Manufacturing Quality team to improve the quality and reliability of their solid-state Li metal batteries. This role involves leveraging data-driven and computational methodologies to detect critical defect modes in cells and develop robust specifications for the manufacturing line. The ideal candidate will have a hard sciences background, experience in the battery or semiconductor industry, and the ability to communicate complex technical information effectively. This is a problem-solving role in a collaborative, fast-paced environment.

Requirements

BS degree in Engineering, Data Science, Statistics, Computer Science, Applied Math, Applied Physics, or equivalent fields. MS or PhD preferred.
5+ years of experience working on highly complex problems in Materials Science, Physics, Chemistry, Engineering, or equivalent fields, such as the battery or semiconductor industries.
Strong programming skills, especially in Python, including 2+ years of experience with data science and machine learning libraries such as Pandas, NumPy, SciPy, scikit-learn, TensorFlow, and PyTorch.
Experience with computer vision and image processing techniques (e.g., image segmentation, object/defect detection, OpenCV) applied to 2D and/or 3D imaging data.
Industry experience with statistical analysis for manufacturing processes, such as regression (e.g., linear, logistic), t-tests, comparison of different test groups, and survival analysis.
Experience developing machine learning models such as tree-based models (e.g., decision trees, random forest, XGBoost) or deep learning models (e.g., neural networks, autoencoders) to predict binary or continuous outcomes using large, complex datasets.
Ability to communicate findings to colleagues from various disciplines through clear and concise reports, presentations, and data visualizations.

Nice To Haves

Fundamental understanding of battery electrochemistries and failure mechanisms.
Familiarity of electrical test and metrics.
Proficiency with SQL to query data from database and data warehouse storage (e.g., GCP's BigQuery).
Experience deploying and monitoring machine learning models in production, or familiarity with MLOps practices for maintaining model performance over time.
Proficiency with AI-assisted tooling for querying, cleaning, and processing data, to accelerate data analysis and visualization, model development, etc.
Proficiency with JMP, Microsoft Office, and VSCode.

Responsibilities

Develop subject-matter expertise on battery components and collaborate cross-functionally on in-line metrology systems and imaging post-processing techniques.
Develop computer vision detection algorithms and machine learning models, including building comprehensive labeling rulebooks, coordinating labelers, and maintain model performance as processes and chemistries change over time.
Collaborate with R&D engineers through weekly in-person team meetings to generate new metrics or deep learning models that capture defect modes in 2D and 3D images.
Leverage advanced statistical and machine learning techniques to uncover complex patterns in large datasets of battery and component-level electrical test outcomes.
Build predictive models that identify key features in metrology and microscopy images of cells, separators, and cathodes to predict downstream electrical performance, and propose opportunities to tighten specifications to drive improved product reliability.
Collaborate with cross-functional engineers to develop repeatable measurement processes for battery cells and components, where data is uploaded to the database and results serve as CTQs and specifications for process-quality tracking.
Leverage AI agents to query manufacturing data and clean and process it, applying critical judgment to select the best data science methodologies and rapidly apply them to internal projects.