Molecular Data Sciences – Principal Scientist M/F
About the Company
Sanofi is a global life sciences company committed to improving access to healthcare and supporting the people we serve throughout the continuum of care. From prevention to treatment, Sanofi transforms scientific innovation into healthcare solutions, in human vaccines, rare diseases, multiple sclerosis, oncology, immunology, infectious diseases, diabetes and cardiovascular solutions and consumer healthcare. More than 110,000 people in over 100 countries at Sanofi are dedicated to make a difference on patients’ daily life, wherever they live and enable them to enjoy a healthier life. As a company with a global vision of drug development and a highly regarded corporate culture, Sanofi is recognized as one of the best pharmaceutical companies in the world and is pioneering the application of Artificial Intelligence (AI) in the R&D organization including drug discovery, chemical manufacturing and control, translational research, clinical development, and regulatory document management and submission. Details of the organization and the company’s mission and goals can be found on our website (http://www.sanofi.us/l/us/en/index.jsp).
Artificial Intelligence (AI) and Machine Learning (ML) algorithms can significantly speed up drug discovery, shorten drug development and identification of patients for clinical trials thereby creating better medicines that save lives.
In this context Sanofi R&D has the clear ambition to accelerate his drug discovery processes by promoting AI/ML technologies combined with Physics-based methodologies.
“Molecular Design Sciences” is a critical group in “Integrated Drug Discovery” Department, one of our Research Platforms that mastered drug discovery of Synthetic Modalities at Sanofi R&D, focused on applications of AI/ML and Deep Learning (DL) algorithms in combination with Computer Aided Drug Design to speed up our process to Identify better Drug Candidates.
Scientists in our group come from diverse backgrounds in computational sciences, structural biology, and medicinal chemistry with strong expertise in AI/ML/DL, Algorithms, Molecular Modeling and Cheminformatics.
We are seeking a Principal Data Scientist to join the “In Silico Science Team” of our group. This group of experts closely interacts with other scientific platforms at Sanofi R&D to identify an optimize compounds along the research value chain from the Early Stage to the Development Candidate milestone in the field of synthetic modalities.
The successful candidate will work with other scientists to apply cutting-edge computation, Machine Learning/Deep Learning approaches to resolve challenges in real-world drug discovery being embedded into the project teams as core member. The successful candidate will contribute to accelerating and improving the process of design, speed-up lead identification and drive the design of novel molecules in lead optimization.
The position is embedded in a team that applies and develops artificial intelligence, molecular data-science, computational methods and platforms to guide drug discovery projects in a high collaborative environment.
The responsibilities of the molecular data scientist in our in-silico group will include
- Apply and develop artificial intelligence and machine learning (AI/ML) approaches (e.g., classification, clustering, machine learning, deep learning) to pharma research data sets (eg activity, selectivity, ADME properties, physico-chemical properties)
- Building models from internal and external data sources, algorithms, simulations, and performance evaluation by writing codes and using state-of-the art machine learning technologies (AI/ML/QSAR) for both large and sparse datasets
- Close interactions with other data scientists as well as research scientists in core scientific platforms focusing on Small Molecule design, in an international context (US, Europe, China)
- Update and report relevant results to interdisciplinary project teams and stakeholders
- Maintain a keen awareness of recent developments in Data Science and Scientific-Computing and state-of-the-art of AI/ML/DL algorithms and research results
- Active engagement in evaluation and coordination of both academic and startup collaborations as well as outsourcing partners
- Promote Digital Culture and Rational Data-Driven decision-making process in Drug Discovery projects
- Apply artificial intelligence methods in combination with first principles physics-based technologies to support the design and optimization of novel drug candidates
- Drive development and usage of de novo design technologies in combination with multiparameter optimization in the context of systematic hypothesis scoring and prioritization
- PhD with a track record of productivity in the areas of a field related to AI/ML or Data Analytics such as: Computer Science, Mathematics, Statistics, Statistical-Physics, Computational Biology-Chemistry or Engineering Sciences
- 3+ years of industry experience with a track record of applying ML/Deep Learning (DL) approaches to solve Molecule or Biological-Macromolecule related problems
- Strong familiarity with advanced statistics, ML/DL techniques including various network architectures (CNNs, GANs, RNNs, Auto-Encoders, Transformers, PLM etc.), regularization, embeddings, loss-functions, Graph theory, Statistical Learning (active learning, optimization strategies, reinforcement learning) technique. Associated expertise in Cheminformatics and Molecular Data-Science
- Proficiency in Python and deep learning libraries (PyTorch, TensorFlow, Keras), RDKit in a Linux/Unix high-performance computing environments on Datacenter or Cloud (e.g., AWS, GCP)
- Familiarity with data visualization and dimensionality reduction algorithms
- Ability to develop, benchmark and apply predictive algorithms to generate hypotheses
- Understanding of pharma R&D processes is a plus
- Fluent in English (written and oral comprehension)
- Fluent in French (written and oral comprehension)
- Team working in a multidisciplinary and multi-cultural environment
- Excellent analytical and problem solving, with a high sense of scientific rigor, as well as communication, scientific writing, and presentation skills
- Able to work within timelines, budget and planning per requirement of drug discovery projects
- Able to have a critical constructive way to interact with putative external collaborators, contractors, or students
- We are expecting this passionate and highly motivated scientists to excel both in skills and behaviors, willing to learn, adopt and contribute to the promotion of our company Play to Win culture, spending time to learn about and understand our sciences and products
- Visionary, innovative and creative the successful candidate will contribute to challenge the status-quo with innovation. Not afraid to take responsibility, to communicate proactively and to present complex issues simply or pedagogically to promote our digital culture
Engaged in the continuous development of our talent, we intend to hire our futures leaders and managers. In this respect multiple career path are possible including international ones.