Applied Research Scientist

InstaDeep, founded in 2014, is a pioneering AI company at the forefront of innovation. With strategic offices in major cities worldwide, including London, Paris, Berlin, Tunis, Lagos, Cape Town, Boston, and San Francisco, InstaDeep collaborates with giants like Google DeepMind and prestigious educational institutions like MIT, Stanford, Oxford, UCL, and Imperial College London. We are a Google Cloud Partner and a select NVIDIA Elite Service Delivery Partner. We have been listed among notable players in AI, fast-growing companies, and Europe's 1000 fastest-growing companies in 2022 by Statista and the Financial Times. Our recent acquisition by BioNTech has further solidified our commitment to leading the industry.

Join us to be a part of the AI revolution!

InstaDeep is looking for Applied Research Scientists to join our BioAI team in London, specializing in the application of classical and machine learning algorithms to the life sciences. In recent years, the advent of artificial intelligence uncovered new tools (such as AlphaFold 2) but also new problems life scientists need to solve (learning vs imitating, underlying biases in biological datasets, lack of data etc.).The Applied Research Scientist role combines elements of research and practical application. Applied Research Scientists will focus on leveraging their deep understanding of scientific principles and research methodologies to address real-world problems and develop innovative products in areas such as protein structure prediction, generative models for structure and sequence, molecular dynamics, protein-protein interactions, and more. The role requires strong collaboration within the BioAI department, as well as across the company, and with our strategic partners, such as BioNTechAn Applied Research Scientist is responsible for developing practical applications for scientific discoveries, and for conducting research that is in line with InstaDeep’s long-term goals. They bridge the gap between theoretical research and real-world implementation by applying their expertise to solve specific problems or develop new technologies.

ROLE RESPONSIBILITIES:

• Design and implement proof of concept methods as well as benchmarking with state-of-the-art methods.
• Leverage classical and/or deep learning biology tools and large biological databases to perform protein design, sequence optimisation, molecular modelling, and other relevant tasks.
• Report and present experimental results and research findings, both internally and externally, verbally and in writing.
• Upon request, collaborate with other groups' activities, including but not limited to presenting the company to new prospective clients, participating in calls and meetings, and representing InstaDeep at conferences/events.

SPECIFIC AREAS OF INTEREST: Computational Modelling:

• Applied research scientists often use computational modelling techniques to complement experimental data and perform in silico macromolecular simulations. They employ molecular dynamics simulations, homology modelling, or other computational approaches to predict protein structures, simulate protein-ligand interactions, or analyze the molecular dynamics of biomolecules.
• Molecular Interactions: Investigate the interactions between biomolecules, such as protein-protein interactions, protein-ligand interactions, or protein-nucleic acid interactions. Applied research scientists use structural information to elucidate the binding modes and dynamics of these interactions, contributing to the understanding of biological processes or the development of therapeutics.
• Proteomics: They develop innovative approaches to leverage language and structure models to extract meaningful information from proteomics datasets, including mass spectrometry data, protein-protein interaction networks, and protein sequence data. Their responsibilities include designing and implementing computational pipelines to preprocess and analyze proteomic data, fine-tuning deep learning models for specific proteomics tasks such as protein function prediction or post-translational modification identification, and integrating model outputs with other experimental or computational data to gain deeper insights into complex biological systems.
• Genomics/Transcriptomics: Employ advanced sequencing technologies and computational tools to analyze large-scale genomic and transcriptomic datasets. Their responsibilities include designing and executing experiments to generate high-quality sequencing data, developing and implementing data analysis pipelines to identify genetic variations, gene expression patterns, and regulatory networks, and interpreting the results to uncover meaningful biological findings.
• Drug Discovery and Protein Engineering: Studying the structures of drug targets and their interactions with potential drug candidates. They apply their knowledge to optimize the binding affinity, selectivity, and efficacy of drug molecules. They also work on protein engineering projects, designing and modifying proteins to enhance their stability, activity, or other desired properties.

REQUIREMENTS

• PhD in Computational Biology, Machine Learning or a related scientific field or equivalent industry experience.

• A strong foundation in biology, biochemistry, and/or biophysics. They understand the fundamental principles of molecular biology and are familiar with the structure-function relationships of biological macromolecules.

• Relevant experience in the application of classical and deep learning algorithms in any of the following domains is highly desirable:

• Structural biology (e.g. protein structure prediction)

• Protein language models

• Multi-omics

• Molecular dynamics

• Protein-protein interactions

• Methods for handling 3D structural data, such as Graph Neural Networks.

• Generative ML models

• The ideal candidate must have extensive experience working with large biological datasets, databases (PDB, Uniprot, etc.) and their API technologies.

• A demonstrated ability to successfully deliver high-quality research, for example through the publication of scientific papers in journals or conferences.

• Excellent communication skills and collaborative spirit.

• Software development skills in Python are necessary.

• Experience using deep learning frameworks such as PyTorch, JAX and/or TensorFlowis a plus.

• Wet lab experience specifically in the areas of biophysical assay development, protein purification and mRNA manipulation is a plus.

Our commitment to our people

We empower individuals to celebrate their uniqueness here at InstaDeep. Our team comes from all walks of life, and we’re proud to continue encouraging and supporting applicants from underrepresented groups across the globe. Our commitment to creating an authentic environment comes from our ability to learn and grow from our diversity, and how better to experience this than by joining our team? We operate on a hybrid work model with guidance to work at the office at least 2 to 3 days per week to encourage close collaboration and innovation. We are continuing to review the situation with the well-being of InstaDeepers at the forefront of our minds.

Right to work: Please note that you will require the legal right to work in the location you are applying for.