2022-2023 Campus Internship - Digital Innovation (Master / Ph.D.)

Our purpose
Join a team that’s passionate about partnership. With careers at Dow, we take time to explore questions and talk to each other. We love to learn. Our people are driven by limitless curiosity.

We are an innovative, customer centric, inclusive, and sustainable materials science company.

• Employing 36,500 individuals
• Across 109 manufacturing sites
• In over 31 countries

Our portfolio of products and solutions include:
Plastics: With new technology trends, our plastic additives can be experienced in many everyday items including vinyl, blow-molding bottles, film, rigid containers, PVC plastics, siding, decks and rails, foam pipes and profile formulations, window frames and high-efficiency lubricants.

Industrial intermediates: As the product of a reaction that is beneficial when used as a precursor chemical for another product, industrial intermediates can take on many shapes and forms. Ours are used in home comfort and appliance, building and construction, adhesives and lubricants, and more.

Coatings: Whether it’s a water-based coating or solvent-based coating, a thin film is deposited on materials to enhance specific properties such as enhanced performance, durability, aesthetics, and sustainability.

Silicone businesses: Our silicone-based materials can withstand more demanding applications, from those operating at extreme temperatures, to those under harsh environmental conditions for long periods of time.

Learn more about our partnerships, collaborations and innovations on LinkedIn (@Dow) or Twitter (@DowNewsroom).

We make diversity and inclusion a priority—because sharing our perspectives and building on each other’s ideas will drive innovation. Could you imagine yourself in a place like this?

Do you want to join Dow's digital innovation journey? We are seeking the brightest Master and Post-Master and/or a Ph.D. interested to complement their primary expertise with an Internship in Digital Science in one of its European sites Terneuzen (Netherlands) or Wiesbaden (Germany), other locations depending on availability.

You will be integrated in one of Dow’s key functions - Research and Development, Integrated Supply Chain, Operations (M&E), or Information Systems. You will work with a cross-functional team whose high-level goal is to accelerate the digital evolution of a global leader in the materials industry. You will bring your skills and experience to work with a group of domain experts to accelerate delivery of high priority projects. Goals of the project(s) could include delivering breakthrough sustainable chemistry innovations; advancing on a circular economy; producing better and safer materials; optimizing products and processes to reduce carbon footprint; optimizing planning, scheduling, and value chain to a greener chemistry; and other areas to help Dow reaching ambitious sustainability goals.

Interns will work with project teams to solve chemical-, material-, and industrial-related problems through both fundamental and applied research. The types of projects span sustainability and circularity, product and process research, application development, operations improvements, and supply chain optimization. The specific opportunities, including project type, geography, and timing, are variable.

Length of Assignment:
Typical duration is 3-6 Months internship (other duration could be arranged). This internship could be part, but not necessary, of a graduating school assignment. Working hours will be the local and legal equivalent of a full-time employee.

Key Traits:
• Experienced in chemical, polymer, and/or material properties; manufacture and/or customer experience of materials; supply chains around manufacturing; and/or the computing/IT systems needed to accomplish the above.
• Primary expertise in chemical engineering, materials science, chemistry, polymer science, theoretical modeling, operations management, or other industrial engineering
• Educated with data science techniques such, machine learning, its applicability to industry, and potential for value creation
• Demonstrate competency in computer science, data analytics, and/or machine learning.
• Able to work independently but also in teams
• Great time-management skills and ability to work under tight deadlines
• Effective communicator, organized and responsive
• Able to quickly assimilate and understand technology, out-of-box thinker

Projects Proposals:
Title: Development of new compatibility chart tool

Description: For rating of the chemical reactivity/compatibility between chemicals, Dow is using an assessment tool, called chemical compatibility chart tool. Currently multiple variants of such a tool (mainly excel based) are in use which all have their disadvantages. The student will develop an internal global uniform (preferably web-based) compatibility with searchable database, leveraging manual assignments from current tools, implement automated logic (based on reactive groups) for ratings which will provide a more uniform and reliable reactivity assessments. The final tool must be easily maintainable.

Skills: Computer Science (prior experience in front-end, back-end development, C#, .NET, and SQL databases..), familiar with PowerBI, Azure DevOps, Git, and Pipelines affinity for chemicals/chemistry

Location: Terneuzen, NL

Title: Improvement to Dow customized Genetic Programming based Symbolic Regression Tool

Description: Dow customized symbolic regression tool find accurate and trustworthy predicting models. Compared to other more sophisticated Machine Learning techniques, the tool does not handle natively nominal variables. An alternative is to use one-hot-encoding but it is unsatisfactory because genetic programming tends to remove such indicator variables due to their discontinuous nature. Kronberger (2018) has proposed another approach, so-called Factor Variables, for representing nominal variables in symbolic regression models. The main advantage in using Factor Variables is that it preserves the underlying fundamental of the predicted functions, and it requires much less data. Another desired improvement is the prediction of confidence intervals. There are approaches applied to symbolic regressions that are worth evaluating such as Bayesian model averaging and Likelihood profiles.

The student would have to: review literature for nominal variables and confidence interval applied to Symbolic Regression, implement chosen solutions in existing MATLAB code, benchmark implementation against literature data, if time allows, the final part of the project would be the deployment of the new solver using MATLAB Production server and Web App server.

Skills: some knowledge of machine learning, regularization, and optimization algorithms, good mathematical and programming skills (knowing MATLAB is recommended)

References: https://sites.google.com/site/gptips4matlab/; https://doi.org/10.1145/3205455.3205522; https://doi: 10.1109/CEC.2014.6900567; https://doi.org/10.48550/arXiv.2209.06454

Location: Terneuzen, NL

Title: Integrated Supply Chain Event Management Data Mining

Description: Dow's Integrated Supply Chain is a customer-driven network of services and capabilities that together ensure the highest level of performance from demand planning all the way through to order fulfillment. ISC operates across the end-to-end value chain to deliver a world-class customer experience. The ISC team is made of more than 4,600 professionals across different locations, and it provides transport management services to 45,000 customer locations in 170 countries, and it drives demand and supply planning for the company. Additionally, the ISC team is responsible to create, manage and execute Order to Cash (OTC) work processes to handle orders, ship and deliver products and receive payments. Supply Chain Event Management (SCEM) is a globally standardized six-step work process that provides leadership and stakeholders with visibility of external events that are or could potentially disrupt the Supply Chain and threaten the ability to service internal or
external customers. SCEM drives actions being taken to mitigate risk and assesses customer impact (actual or potential).

The student will create a structured database from past event data (more than 10 years data) and use modelling and predictive analytics to detect trends and anticipate risks and create a new SCEM submission form to collect data for future events in a structured way

Skills: experience with data mining and modelling

Location: Terneuzen, NL

Title: Development of an extrusion coating simulation tool

Description: A model had been developed to predict neck-in and draw-down in extrusion coating, but was not deployed into a user-friendly tool which limits its use. Lead times to run extrusion coating experiments internally are long. An easy-to-use tool to predict performance of extrusion coating resins has the potential to save many hours of trials and optimize the selected experiments in real-life trials. The tool would be used in support of a product launch and other implementations with key customers. The model is currently available in MATLAB code. The student will interface those codes in Web applications (MATLAB WebApp), validate the tool against trial data, and eventually could build a library of parameters and do some analysis to evaluate alternative input data.

Skills: UI development, Matlab WebApp, knowledge SQL

Location: Terneuzen, NL

Title: Silicon polymer production data analysis

Description: Dow Performance Silicones has been a global leader in silicone-based technology for more than seventy years with >7000 silicone products in the market. Dow SylgardTM silicone dielectric gels are among the most well-known products offered by Dow Performance Silicones. By possessing properties such as high elongation and low hardness, these gels are widely used for coating, encapsulating, potting, and sealing electronic devices.

Quality control on key raw materials used for the gel production is critical to ensure these gels’ consistent high performance. Over the years, there has been a large data library comprising several process steps and their quality test results for the production of these key raw materials. It is envisioned that an in-depth data analysis of this library would be highly beneficial in providing valuable information for both good product quality control and future continuous production improvement.

Skills: We are looking for a digital intern with outstanding skills with Excel or any other data and statistical analysis programs, general programming skills and hand-on experience to work with large numerical data set.

Location: Wiesbaden, Germany

Required Qualifications:
• You are currently enrolled in a graduate school (Master and Post-Master level or equivalent) and/or a Ph.D. degree program in Chemistry, Chemical Engineering, Mechanical Engineering, Material Science, Polymer Science, Computer Science, Mathematics, Operations Research, Data Science, or other related disciplines.

Preferred Qualifications:
• You are a student currently enrolled in graduating either as a Master, a Post-Master level or Ph.D. in the disciplines listed above are preferred.
• You are proficient in one or more programming languages, e.g., Python, R, Matlab and educated in data science techniques (regression, classification, clustering, Deep learning, NLP....) and their tools such Pandas, Azure AutoML, Scikit-learn, PyTorch, TensorFlow, NLTK, SQL/NO SQL...)

About Dow
Dow (NYSE: DOW) combines global breadth; asset integration and scale; focused innovation and materials science expertise; leading business positions; and environmental, social and governance leadership to achieve profitable growth and help deliver a sustainable future. The Company's ambition is to become the most innovative, customer centric, inclusive and sustainable materials science company in the world. Dow's portfolio of plastics, industrial intermediates, coatings and silicones businesses delivers a broad range of differentiated, science-based products and solutions for its customers in high-growth market segments, such as packaging, infrastructure, mobility and consumer applications. Dow operates manufacturing sites in 31 countries and employs approximately 37,800 people. Dow delivered sales of approximately $57 billion in 2022. References to Dow or the Company mean Dow Inc. and its subsidiaries. For more information, please visit www.dow.com or follow @DowNewsroom on
Twitter.

As part of our dedication to the diversity of our workforce, Dow is committed to equal opportunities in employment. We encourage every employee to bring their whole self to work each day to not only deliver more value, but also have a more fulfilling career. Further information regarding Dow's equal opportunities is available on www.dow.com.