Scientist I/II, Protein and Chemistry Machine Learning

We are seeking a highly motivated machine learning scientist to join the Chemical Data Science team. The Chemical Data Science team is tightly integrated with protein and structural sciences, medicinal chemistry, chemical proteomics, and plays an important role in drug discovery project teams. The successful candidate will be responsible for the development and implementation of data analytics and machine learning methods to enable target prioritization and drug discovery efforts.

Responsibilities can include

• Development and implementation of advanced data analytics and state-of-the-art machine learning models to generate insights from proteomics (ABPP) data, protein structure, and protein dynamics to enhance target prioritization and structure-based drug design efforts
• Development and validation of predictive models for GSH reactivity, cysteine reactivity, and ADME properties of small molecules
• Deployment and fine-tuning of generative chemistry approaches
• Be an integral, proactive member of a highly interdisciplinary team and drug discovery projects
• Stay up-to-date with the latest advances in machine learning and drug discovery
• Contribute to the development of our computational infrastructure by identification and incorporation of novel tools in collaboration with the Data Science and broader Scorpion team

Qualifications

• PhD or MSc in computational biophysics, computational chemistry, chemical engineering, computer science, machine learning or related field
• Extensive hands-on experience with ML methods in chemistry, and/or structural biology
• Experience with data analytics approaches related to the large heterogeneous proteomics data sets
• Strong scientific programming skills with Python
• Experience with at least one open-source high-end development environment such as PyTorch or TensorFlow
• Familiarity with code versioning tools (Git/GitHub)
• Experience with RDKit, OEChem, Schrödinger, or other cheminformatics and computational chemistry toolkits
• Experience with cloud computing infrastructures (AWS preferred)
• Excellent problem-solving skills and ability to balance the tradeoffs between the speed and quality while working independently in a fast-paced, highly collaborative environment
• Great communication skills, both written and verbal

Nice to have

• Post-PhD/Msc work experience in an industry/biotech setting
• Experience with development of data processing workflows and infrastructure
• Practical experience developing deep generative methods in chemistry
• Demonstrated experience developing software in a team setting
• Familiarity with CICD and MLOps