Modeling Scientist

Position Overview

Novelis is one of the world leaders in aluminum recycling and rolling and a leading sustainable aluminum solutions provider. Driven by our purpose of shaping a sustainable world together, we work alongside our customers to provide innovative solutions to the aerospace, automotive, beverage packaging and specialty markets. Headquartered in Atlanta, Georgia, Novelis has approximately 13,000 employees in 32 operating facilities on 4 continents.

The Modeling team, located in Kennesaw, GA is seeking a Modeling Scientist. This role is responsible for the development and deployment of multi-physics, multiscale materials modeling and physics guided artificial intelligence modeling capability within Novelis to accelerate discovery and development of sustainable products and processes.

A major focus is bridging microstructural length scales, as applied to Novelis’ products (aluminum sheet and plate) and its manufacturing processes (aluminum casting, rolling, heat treatments etc.), and development of a deeper understanding of alloy chemistry - thermomechanical processing – microstructure – property – product performance relationships using physics-based approaches like large scale crystal plasticity finite element modeling and data-driven approaches like machine learning and high-throughput computations.

Working closely with the metallurgists, product, process, and application engineers at the Customer Solution Centers, the successful applicant will apply their modeling expertise to a variety of technical challenges related to industrial sheet metal production and the manufacturing of complex products. The successful applicant will have the ability to gather critical materials inputs for their models as well as to test their ideas under close to real-world conditions by employing Novelis’ substantial laboratory testing and characterization facilities and pilot-scale equipment before scale-up to Novelis plants or customer operations.

There will be opportunity to travel, to collaborate with our extensive network of academic and industrial partners, colleagues in Novelis’ worldwide plants, regional research and technology centers and Customer Solution Centers around the globe and to directly support our customers. The role will involve working in and leading multi-disciplinary teams to combine modeling with experimental work for maximum impact on the speed and depth of our materials research.

The role provides significant potential for technical growth and a real chance to impact the future success of Novelis’ global businesses.

• Act as company-wide subject matter expert for multiscale, multiphysics modeling and application of machine learning to materials modeling in support of global R&D projects.
• Establish advanced materials and data driven models to develop capabilities that will guide and accelerate development of transformational and sustainable products and processes.
• Design, develop, and validate statistical and machine learning models for prediction, optimization, and simulation
• Build end‑to‑end ML workflows and pipelines, including data ingestion, feature engineering, training, evaluation, versioning, and deployment
• Define and lead modeling driven projects to address critical product and process development challenges.
• Partner with wide range of internal specialists to develop solutions e.g., with product metallurgists, rolling process engineers, formability, surface, corrosion and computational material scientists.
• Establish and lead supporting partnerships with universities, national labs and other external organizations.
• Support wider adoption and application of both physics and data driven modeling tools amongst other specialists.
• Collaborate with colleagues to develop associated experimental programs that provide supporting data or understanding critical to model development.

• PhD in metallurgy, metallurgical engineering, materials science/engineering or mechanical engineering.
• Minimum experience of 2+ years in multiscale, multiphysics modeling and application of machine learning after PhD completion gained in…