Companies you'll love to work for

","datePosted":"2023-10-10T14:14:46.366Z","validThrough":"2023-12-18","employmentType":[],"hiringOrganization":{"@type":"Organization","name":"CHARM Therapeutics","description":"Harnessing the power of deep learning on 3D molecular configurations to deliver medicines of transformational efficacy to patients.","numberOfEmployees":59,"address":[{"address":{"@type":"PostalAddress","addressLocality":"United Kingdom"}},{"address":{"@type":"PostalAddress","addressLocality":"London, UK"}},{"address":{"@type":"PostalAddress","addressLocality":"Mile End, London, UK"}}],"sameAs":"","url":"","logo":"","memberOf":{"@type":"Organization","name":"F-Prime Capital Partners","description":"F-Prime Capital is a global venture capital firm investing in healthcare and technology, with a heritage that spans four decades.","logo":"","url":""},"keywords":"Biotechnology, Data and Analytics, DeepTech, Software"},"jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"Cambridge, MA, USA"}}}

Principal Scientist, Modelling & Informatics

CHARM Therapeutics

CHARM Therapeutics

Cambridge, MA, USA
Posted on Tuesday, October 10, 2023

Principal Scientist, Modelling & Informatics

CHARM Therapeutics is a biotech focused on delivering transformational medicines that will address difficult-to-drug targets in key oncogenic pathways. CHARM has developed the first highly accurate, high throughput protein-ligand co-folding algorithm (DragonFold), driven by end-to-end 3D deep learning.  Our platform enables the rapid generation of highly differentiated clinical candidates, our ambition is to revolutionise drug discovery. 

CHARM Therapeutics has a state-of-the-art R&D facility in Cambridge, UK.  We are seeking an experienced Computational Chemist with a passion for scientific innovation.  The successful candidate will join a multidisciplinary, highly collaborative discovery team to drive our oncology-focussed drug discovery pipeline and invent novel medicines.  Utilising innovative computational chemistry problem-solving skills and leveraging CHARM’s 3D-Deep Learning Design platform, he/she will enable the design of new molecules to drive our oncology pipeline.  In this role, the incumbent will contribute to the overall scientific deliverables of the research site by helping to define CHARM’s computational chemistry strategy, and drive internal programs.   Furthermore, he/she will engage with the external scientific community to further our scientific activities and build CHARM’s external reputation.  To accomplish the above, the successful candidate will have excellent interpersonal, cross-functional collaboration and communication skills, in addition to rigorous scientific thinking.


Role Responsibilities:

Help define the computational chemistry strategy for CHARM, and in conjunction with other CHARM leaders, help define overall strategy for drug discovery projects from Target ID to candidate nomination 

Apply a breadth of computational chemistry techniques to accelerate the evolution of drug discovery leads to drug candidates in a hypothesis-driven manner

Use timely decision making to ensure focus and delivery of key project objectives.  Promote high levels of productivity and urgency, leading by personal example

Collaborate with CHARM’s ML/AI and data engineering teams to evolve the DragonFold platform and enable further applications to drug discovery programs

Lead and/or contribute to cross-functional goals within CHARM

Foster collaborations within CHARM and with academia to help ensure that the computational chemistry group operates at the highest levels of scientific excellence 

Continue research in areas of computational chemistry relevant to drug discovery and maintain an external scientific presence through authoring significant scientific publications and presentations


Educational Background:

A PhD in Computational Chemistry, Biophysics, Chemistry, Biochemistry, or equivalent is preferred.  A degree with a computational chemistry emphasis is preferred.


Skills and Experience required:

A minimum of 8 years of relevant industry experience in drug discovery 

Experience with Linux and high-performance computing

A strong knowledge of the latest innovations and technology in computational chemistry, and an openness to explore new methods for drug discovery

A strong knowledge of compound design principles, including structure-based drug design and the influence of physicochemical properties 

Experience of working across multiple target-types and gene families

An understanding of the process of finding new drug discovery targets, and how computational chemistry can contribute to target validation

A creative and strategic thinker who can enthuse the computational chemistry group and beyond with innovative and winning ideas

A good understanding of the related scientific disciplines that are pertinent to drug discovery (e.g. chemistry, pharmacology, chemical biology, ADME, structural biology & drug safety/toxicology) 

The ability to thrive on increasing levels of responsibility 

Effective communication skills, both verbal and written

The ability to influence and drive change at all levels and across disciplines

Collaborative, with the ability to work well as part of a multidisciplinary team

Track record of training, mentoring and managing a computational chemistry team

The ability and desire to foster academic networks such that CHARM remains an outward looking organisation that can exploit the world’s best scientific thinking

Multiple publications and external presentations demonstrating creative application of computational chemistry approaches to problems of biological interest

The ability to work flexibly across the CHARM portfolio


The following skills may be advantageous:

Ability to effectively apply molecular modelling packages such as Openeye Toolkits and RDKit (what we use currently)

Understanding and practical application of free energy perturbation, MM-GBSA and other molecular dynamics-based methods

Understanding and practical application of machine learning methods for compound design. Experience using statistical machine learning frameworks such as sci-kit learn and deep learning frameworks such as pytorch.

Scripting and programming expertise in languages such as Python

Experience applying computational methods such as molecular dynamics, quantum chemistry, and machine learning to problems of pharmaceutical interest