Cheminformatics Data Scientist required to join a start-up working at the intersection of Machine Learning, Chemistry and RNA Biology. My client is building an in silico/vitro platform that will enable researchers to find small molecule RNA modulators.
You will collaborate closely with the Machine Learning and Medicinal Chemistry teams to develop the tools and platforms required to design unique chemistry, enable hit-to-lead optimisation programmes, and expand the chemical universe. This will entail using cutting-edge machine learning algorithms to influence the chemistry we utilise in drug discovery and have an impact on patients' lives. To do so, you'll collaborate with expert medicinal chemists to provide insights and conclusions from biology, chemistry, and computer science to our drug discovery process. As well as this, you will influence the ML Engineering frameworks and core ML-infrastructure, establishing the data and engineering strategy ensuring we are set up to scale our platforms.
Responsibilities and duties;
• Prior experience with implementing in silico molecular design, state of the art machine learning frameworks, or multi-parameter optimisation.
• Demonstrated ability to write production-ready code: readable, well-tested, experience with at least one high-end ML development environment (Tensorflow, Pytorch, Caffe, etc).
• Ability to effectively communicate findings to those with chemical and computational domain understanding, as well as non-expert scientists from other fields.
• Peer-reviewed publications and/or a personal GitHub repository showcasing your excellence in machine learning in chemistry.
Qualifications;
*Must have Cheminformatics/Computational Chemistry/Drug Discovery experience*
• PhD in cheminformatics or machine learning applied to drug discovery / chemistry
• Experience in the application of machine learning to drug discovery and cheminformatics tool kits (OpenEye, RDKit)
• Good coding skills, preferably in Python
• Creative, problem solving skills
• Translation abilities – your curiosity allows you to work across domains
• Desire to work in a small team, making an impact at pace
• Familiarity with the classical data science stack (sklearn, numpy, scipy, pandas) and deep
learning frameworks (PyTorch or TensorFlow) and at least one MLOps tool (MLflow, DataBricks,
Comet, Neptune, W&B, Kedro, Kubeflow, etc).
• Cloud native: familiarity with AWS and/or GCP products: VMs, clusters, networking, EC2, EMR, RDS, Redshift.
• 2+ years of experience developing and delivering robust ML software solutions, ideally within
the agile framework
• In depth understanding of data structures, data modeling, database management
• Advanced knowledge of SQL and experience working with relational and other databases
