Lead Data and Solution Engineer - Molecular Design

Key Skills

Aartificial intelligence, Data Catalog, Data pipelines, Data science techniques, ETL frameworks, Machine learning techniques, Python Programming

Job Description

You will be part of the Data Management & Informatics (DMI) department and the Data Products Organization, where we are responsible for providing scientific data and software products to support the global research and early development organization at Novo Nordisk. Our work spans driving digitalization of laboratories, enabling scientific data capture, creating harmonized data for analytics, and providing informatics tools. We enable disruptive innovation and data driven decision making across areas that include disease understanding, molecular design, portfolio management and external scouting. We have a strong focus on employee engagement, and on developing and retaining talent. 

Working at Novo Nordisk 

At Novo Nordisk, we don't wait for change. We drive it. We're a dynamic company in an even more dynamic industry, and we know that what got us to where we are today is not necessarily what will make us successful in the future. We embrace the spirit of experimentation, striving for excellence without fixating on perfection. We never shy away from opportunities to develop, we seize them. From research and development, through to manufacturing, marketing and sales - we're all working to improve patient care. 

The Position

This Data and Solution Engineer position is responsible for developing data products for pharmacology and therapeutic molecule development organizations. You will partner with stakeholders to contribute to the design of the data product roadmap and implement key features to deliver consistent access to existing and new data. Pharmacology and related modalities require architecting data pipelines to solve complex scientific problems. You will contribute directly to building the data pipelines leveraging artificial intelligence (AI) methods to discover new therapeutics. You will contribute to the full lifecycle spectrum of data products through technical guidance and implementations. Starting with data from internal and external sources, you will identify and describe requirements to find, access, consume, protect, and reuse molecular data across research and early development phases and therapeutic areas. Data may include multiple types, such as cheminformatics databases, custom file types, processing pipelines, Python code, compound catalogs, dynamics, docking, molecular structure, and more. Machine learning models and pipelines will play an increasing role in data products and will be part of the product roadmap. You will work with scientific architecture leads, data scientists, and computational chemists to understand, capture, and implement functionality that deliver a data product. It is important to utilize existing tools to handle software versions, model performance metrics, data provenance, and restrictions on sensitive data used in training and testing. We welcome and value your input how our tools and processes can be improved; always improve and share new ideas. Understanding how to create robust and extensible products which are flexible for complex and often ambiguous requirements will be essential.

You will collaborate and partner with various stakeholders such as computational scientists, data scientists, automation platform specialists, experimental scientists, and external partners. Your experience in computational molecular modeling and data workflows will be essential to shape data products. The development of a roadmap will evolve over time to develop new features and rigor of service levels. Key stakeholders will include data scientists, experimental scientists, and scientific project leaders. You will partner with data products engineering teammates to identify existing technical platforms or otherwise highlight technology or process gaps essential to the roadmap. 

You will build based on requirements, created under an agile framework. It is important to ensure not only implementation of tooling and pipelines but equally necessarily to document and design testing and validation methods to define readiness; whether a software method or manual process. This will allow data engineers and data architects to successfully use continuous integration and continuous delivery.

You will be a key contributor who can influence process and understand requirements of chemists, computational modeling scientists, and biophysical experimentalists, with the goal of changing how data is captured and championing requests from data generation stakeholders. This requires aligning with other product owners and specialists across DMI and Global IT to address larger needs.

Do you believe that the digitalization transformation in Research and Early Development (R&ED) is crucial for the success of pharmaceutical companies in the future? Then apply to become part of the next wave of scientific discovery by joining Digital Science & Innovation (DSI). 

Relationships

The Data and Solutions Engineer reports to the Sr. Director, Data and Solutions Engineering, Modalities and Pharmacology. Internal partners include therapeutic area scientists, computational biologists, data and software engineers, software developers, platform and compute engineers in Research and Development and Information Technology. External relationships include commercial and academic collaboration partners.

Essential Functions

The Data and Solution Engineer role will implement the molecular design data product to enable Global Research Technology to accelerate using our data for therapeutics discovery and early development. 

You will: 

• Create data pipelines from raw sources to cloud services. This involves understanding the data to improve future data generation methods. Implementing ETL methods that can accommodate very large hierarchical data as well as streaming data, in addition to traditional data types like tabular stores.

• Implement pipelines that use cheminformatics and molecular modelling tools in conjunction with AI methods to transform and analyse datasets in preparation for the data product platform. This is important to create robust and adaptable systems to address automation needs for data curation backlogs.
• Gather, organize, and transform large, complex datasets while developing processing pipelines, and additionally, you'll establish automated monitoring to ensure pipeline and database compliance and integrity. 
• Being a key contributor to agile product delivery teams, concentrating on publishing data products to the data catalog, platform engineering, and providing clinical research data, while prioritizing tasks based on business needs and ensuring accessible and well-utilized imaging data for scientists and data scientists. 
• Proficiency in DevOps concepts such as continuous integration and delivery, along with expertise in facilitating efficient data sharing via cloud, accelerated computing, and AI/ML strategies, while also assisting in provisioning compute and data pipelines to ensure high-performing delivery of diverse data products within the research and enterprise data ecosystem. 
• Optimize workflows for research imaging data, facilitate global data exchange, ensure researchers' proficiency in preferred applications, and collaborate to develop or acquire new systems and software with both internal and external partners. 
• Advocate for data and data science utilization, including computational and machine learning methods, within research projects, while also contributing to the maintenance and support of various tools and applications like Python, R, Jupyter Hub, Domino, and DataLab. 
• Collaborate and be transparent

   

Physical Requirements

Up to 10% overnight travel required.

Qualifications

• Master’s degree, or PhD in Life Sciences, Biomedical Engineering, Physics, Statistics, or Computer Engineering is preferred. Bachelor’s degree with 8+ years’ relevant experience may also be considered;
• Master’s degree with 5+ years’ relevant experience, or PhD with 4+ years’ relevant experience can be considered
• Relevant experience includes:
• Experience in the life sciences, chemistry, biotechnology, medical device, or pharmaceutical industry. 
• Demonstrated experience in constructing and operationalizing ETL data pipelines, combined with proficiency in databases (SQL, Oracle, NoSQL) and cloud technologies such as AWS S3, DynamoDB, and Lambda. Be knowledgeable in working with structured and unstructured datasets.
• Working experience in cheminformatics, quantum mechanics, or similar atomic / molecule pipelines. It is especially important to have experience working with AI workflows. Any working knowledge of large language models (e.g. ChatGPT) for scientific applications is a significant advantage. This includes accounting for molecular properties used in machine learning workflows. 
• Have proficiency is a variety of data types associated with molecular modelling or complex chemistry compute workflows. Need to understand how to represent modified peptides or RNA molecules using formats like SMILES, PDB, etc.
• Ability to work independently while being open to occasional guidance from managers or senior colleagues, with a preference for automated testing skills; additionally, excellent communication skills are required, both in interactions with bench scientists and end-users, as well as with middle management. 

The role calls for a genuine passion to comprehend scientists' use cases, coupled with a broad expertise encompassing data and digital realms, including hands-on technical proficiency. Strong analytical skills, meticulous planning, and the capacity to design robust, scalable solutions in a structured and detail-oriented manner are essential. 

We commit to an inclusive recruitment process and equality of opportunity for all our job applicants.

At Novo Nordisk we recognize that it is no longer good enough to aspire to be the best company in the world. We need to aspire to be the best company for the world and we know that this is only possible with talented employees with diverse perspectives, backgrounds and cultures. We are therefore committed to creating an inclusive culture that celebrates the diversity of our employees, the patients we serve and communities we operate in. Together, we’re life changing.