Responsibilities
Design, build, and deploy production-grade ML models for predictive analytics and condition monitoring applications across tire products and manufacturing domains, moving solutions from prototype to operational systems used by engineering teams
Apply physics-informed and hybrid physics-ML approaches that embed domain engineering knowledge directly into model architectures, ensuring predictions are physically consistent and trusted by engineering stakeholders
Develop and deploy computer vision systems for image-based inspection and classification tasks
Build and maintain scalable data pipelines for ingesting, processing, and serving high-frequency sensor streams from connected physical systems, supporting both real-time and batch analytics use cases
Implement Generative AI and LLM-based tools to enhance engineering productivity, including knowledge retrieval systems and AI-assisted workflows, with emphasis on on-premises deployment too
Build and operate end-to-end MLOps infrastructure: experiment tracking, model registry, automated retraining, data drift monitoring, and production model serving to maintain model quality throughout the product lifecycle
Partner with R&D, simulation, vehicle dynamics, and manufacturing engineering teams to identify AI opportunities, translate domain requirements into ML problem formulations, and drive adoption of AI-powered tools
Mentor junior ML engineers, conduct code reviews, and contribute to the continuous growth of the team's technical capabilities and delivery standards
Skills & Qualifications:
Master's degree (or Bachelor's with strong experience) in
Mechanical Engineering, Aerospace, Materials Science, Electrical Engineering, Applied Physics, or a related engineering discipline
;
Minimum
6-8 years of applied AI/ML engineering experience with a physical engineering domain component
Demonstrated track record of
deploying ML models into production environments used by engineering teams or operational systems
— not prototype-only work
Proficiency in
Python ML stack (PyTorch, TensorFlow, scikit-learn)
and hands-on experience with
physics-informed or physics-hybrid ML
; ability to assess model outputs for
physical consistency
Experience with
sensor or time-series data from physical systems (industrial, automotive, aerospace, or equivalent)
including
signal processing (FFT, wavelet decomposition, feature extraction from vibration/acceleration data)
Practical experience building
RAG pipelines or LLM-integrated workflows in engineering or industrial contexts; familiarity with local LLM deployment for IP-sensitive environments
MLOps and deployment skills: MLflow or equivalent experiment tracking, Docker/Kubernetes, CI/CD for ML, cloud ML platforms (AWS SageMaker, Azure ML, or GCP Vertex AI), and production model serving
Strong cross-functional communication skills — able to explain model uncertainty to a test engineer and tire mechanics to a data scientist; experience collaborating with non-ML engineering stakeholders
Preferred: background in tire, automotive, motorsport, or industrial manufacturing domains; familiarity with FEA tools (Abaqus, ANSYS) as data sources; experience with edge AI deployment (
TFLite, ONNX, TinyML
)
Comfortable working in a global, matrixed organization across multiple time zones and regions; able to collaborate effectively with distributed engineering and business teams in the Americas, Europe, and Asia-Pacific
#Li-Hybrid
#Li-APGY
Goodyear is one of the world's largest tire companies. It employs about 63,000 people and manufactures its products in 49 facilities in 19 countries around the world. Its two Innovation Centers in Akron, Ohio, and Colmar-Berg, Luxembourg, strive to develop state-of-the-art products and services that set the technology and performance standard for the industry. For more information about Goodyear and its products, go to www.goodyear.com/corporate
Goodyear is an equal employment opportunity employer. All qualified applicants will receive consideration for employment without regard to any characteristic protected by law.
