Overview:
Come help us research and develop self-diagnosing, self-healing instruments!
The Waters Global Research department is exploring state-of-the-art capabilities that will stretch your creative talents. Our aim is to enhance our customers’ user experience by building more intelligent systems. Our analytical chemistry instruments have a direct impact on laboratory testing, drug discovery and development and food safety, and we strive to enhance our software offerings, making them more intuitive and easier to use.
The current work focuses on training machine learning and other statistical models that perform root error diagnosis using raw signals time series data coming from our instruments. Other projects include automating steps that users currently do manually, such as interpreting raw data results, adjusting anomalous data to clean it up, and optimizing the procedures that the instruments run on.
The role of this coop is to aid the team to collect and augment specialty instrument data, develop time series classification and prediction models, and experiment with new data features as well as new algorithmic features to maximize the efficiency and efficacy of the results. We are looking for someone with a growth mindset who is self-motivated, and ready to overcome obstacles to develop a working research prototype.

Responsibilities:

• Support the staff ML Engineers to build out new techniques to improve the models
• Create baseline models, and build/improve the test harness to properly compare alternatives
• Use object-oriented programming and functional programming best practices to maintain codebases and write unit tests
• Contribute to the construction and maintenance of the AWS data pipeline

Qualifications:

• Strong skillset in Python programming language, Numpy, Pandas and Scipy libraries
• Ability to comfortably and naturally write code in an object-oriented way
• Knowledge / experience with machine learning models
• Knowledge / experience reading online references and research literature and applying algorithms to the code
• Comfortable with Git version control, BASH shell, and virtual environments

DESIRED (CONSIDERED A PLUS) QUALIFICATIONS:

• Knowledge/experience with AWS Lambda, S3 and Sagemaker
• Knowledge and class experience with Bayesian inference
• Experience designing high performance algorithms
  Company Description:
  Waters Corporation (NYSE:WAT) is a global leader in analytical instruments, separations technologies, and software, serving the life, materials, food, and environmental sciences for over 65 years. Our Company helps ensure the efficacy of medicines, the safety of food and the purity of water, and the quality and sustainability of products used every day. In over 100 countries, our 7,600+ passionate employees collaborate with customers in laboratories, manufacturing sites, and hospitals to accelerate the benefits of pioneering science.
  Diversity and inclusion are fundamental to our core values at Waters Corporation. It benefits our employees, our products, our customers and our community. Waters complies with all applicable federal, state, and local laws. Qualified applicants are considered without regard to sex, race, color, ancestry, national origin, citizenship status, religion, age, marital status (including civil unions), military service, veteran status, pregnancy (including childbirth and related medical conditions), genetic information, sexual orientation, gender identity, legally recognized disability, domestic violence victim status, or any other characteristic protected by law. Waters is proud to be an equal opportunity workplace and is an affirmative action employer. All hiring decisions are based solely on qualifications, merit, and business needs at the time

• Support the staff ML Engineers to build out new techniques to improve the models
• Create baseline models, and build/improve the test harness to properly compare alternatives
• Use object-oriented programming and functional programming best practices to maintain codebases and write unit tests
• Contribute to the construction and maintenance of the AWS data pipelin