Applied Research Scientist, AI (RNA modelling)

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, Kigali, Cape Town, New York, 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!

As BioNTech's AI research organisation, InstaDeep is leading the AI revolution in biology, with breakthroughs like the Nucleotide Transformer [1], ProtBFN [2], and InstaNovo [3]. In the RNA group, we develop new fundamental and applied AI technologies for RNA science, the foundation of BioNTech's work, which includes the first Covid vaccine [4] and the world's leading personalised immunotherapy programme [5].

As an Applied Research Scientist in AI, you will take a lead role in addressing the most important challenges in RNA science. Working closely with biologists and engineers, you will develop new foundational and generative models, new methods of RNA optimisation and design, and ultimately identify new fundamental RNA biology. You will have access to one of the most powerful compute clusters, collaborate with world-leading experts to train models on unique proprietary data, and validate them in BioNTech's high-throughput labs.

Your work in this role will directly influence life-saving therapies in cancer and other serious diseases. We are passionate about using science to help people and advance human knowledge. Our culture is highly collaborative and focuses on team success over individual achievement.

Role Responsibilities

• Work on novel optimisation methods for discrete sequence spaces, integrating constraints from biology and wet-lab feedback.
• Develop foundation and generative models for biological sequences using cutting-edge techniques (transformers, diffusion models, large-scale pretraining).
• Address core ML challenges: heterogeneous data fusion, low-data generalisation, and multi-modal pretraining.
• Train at scale on InstaDeep's 0.5 exaflop H100 cluster with dedicated compute resources.
• Collaborate with domain experts to validate models in real-world settings, design laboratory datasets, and iterate based on experimental results.
• Keep abreast of emerging developments and share these with colleagues.
• Contribute to novel therapeutic technologies and the advancement of RNA science.

Requirements

• PhD or postdoctoral experience in Mathematics, Physics, Artificial Intelligence or a related field, or equivalent professional research experience.
• Proven track record of high-quality research, as demonstrated by publications in leading journals or conferences.
• Strong mathematical intuition.
• Strong programming experience.
• Excellent scientific communication skills, both written and verbal, with multidisciplinary technical and non-technical audiences.
• Preference for working as part of a team towards a common goal.
• Passion to advance research that contributes directly to treatments for serious diseases.

Beneficial

• Research experience in AI for biology. Experience with RNA science is especially relevant.
• Experience mentoring or leading research teams.
• Software engineering skills in Python.
• Expertise in deep learning frameworks.
• Experience in any of these areas: large scale / foundation models; generative models, especially for biology; AI interpretability.
• Familiarity with any of the following fields: statistically modelling; advanced linear algebra; differential equations; high dimensional geometry; graph theory; information theory.

References

• [1] Nucleotide Transformer: building and evaluating robust foundation models for human genomics
• [2] Protein sequence modelling with Bayesian flow networks
• [3] InstaNovo enables diffusion-powered de novo peptide sequencing in large-scale proteomics experiments
• [4] BioNTech has partnered with the UK government to treat 10,000 patents by 2030.
• [5] InstaDeep's compute cluster Kyber is in the top 20 most powerful H100 GPU clusters and top 100 most powerful compute clusters worldwide.

* Please upload your CV/Resume in English *

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 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 without visa sponsorship in the location you are applying for. We do not sponsor work visas.