About the role

The Computational Drug Discovery team is looking for a Research Scientist - Protein Representations. You will have the opportunity to contribute to Owkin’s biopharma endeavors by using and developing state-of-the-art methods for protein representation and optimization. You will be involved in internal R&D projects using both machine learning expertise and domain knowledge.

In this role**,** you will support our internal drug discovery programs, as well as develop new machine learning algorithms to accelerate those activities.

You will work in R&Tech, under the supervision of the Computational Drug Discovery team lead.

In particular, you will:

• Bring state-of-the-art protein langage models to Owkin
• Develop ML libraries & workflows for protein design
• Develop methods combining 3D structure and sequence to solve tasks relevant to Owkin
• Help develop tools for target assessment
• Support our internal drug discovery pipeline
• Write scientific papers and project reports, participate in scientific conferences
• Participate in our internal R&D, striving to keep Owkin’s methodology to the state-of-the-art

About You

Above all, you should be excited by the idea of working at the intersection of drug discovery and machine learning.

The successful candidate will have a ‘team-first’ kind of attitude; be independent, curious and detail-attentive; thrive in a dynamic, fast-paced environment; and be fun to work with.

In terms of skill set, we are looking for someone with:

• MSc/engineering degree with a few years of relevant research experience; or PhD in Computational Chemistry, Machine Learning, (Bio)Physics, Mathematics, Statistics or related fields.
• Demonstrated expertise in protein language models and/or the application of 3D-aware models to protein representation (point cloud, 3D GNNs, etc.) including publications at top conferences and journals,
• Strong programming skills in Python with good software engineering skills.
• Knowledge and experience with machine learning toolkits and concepts (scikit-learn, classical algorithms, cross-validation, statistical tests, …). Hands-on experience with deep learning frameworks (Tensorflow, PyTorch, etc.).
• Working biochemistry knowledge, experience working with protein or biologics data (both sequence and structure).
• General knowledge of the drug discovery process, constraints and timelines.
• Excellent written and oral communication skills. Fluent in English.
• Comfortable working in cross-disciplinary teams, highly organized, capable of tackling complex problems logically and effectively, self-driven.

Ways to Stand Out

We would be especially excited to read about your:

• Prior experience in a drug discovery setting
• Experience working on antibodies or protein design
• Experience with fine-tuning of language models
• Experience with 3D data (point clouds, E(3) equivariant models, etc.)
• Experience with visualization and understanding of protein structures

For Internal Use: #LI-CJI