PhD Research Internship

AI for drug design is starting to have real world impact but most companies struggle deploying AI effectively as they lack data and expertise. deepmirror is a drug design Foundation Model built from curated, non-public experimental molecule property measurements (potency, binding, ADMET) aggregated from patents, papers, and partners. We help chemistry teams choose the next best experiments to progress programs faster with fewer dead ends. Since launching in 2023, our platform is now used by hundreds of chemists across the globe to impact real world drug programs in oncology, dementia, infammation, and global health. Now, we are looking for an experienced PhD student to supercharge our product.

In the role you will research and develop key features to solve real world challenges of AI in drug discovery. This is an outstanding opportunity for someone who wants to be involved from day 1 of the start-up journey and who wants to put new processes into place to build a powerful platform in a high performing & collaborative team, based in the beautiful location of Victoria House in the heart of London. With a strong focus on Python programming and advanced backend technologies, we encourage you to seize the opportunity to be independent and drive innovation and quality. In the role, you will have substantial growth opportunities, allowing you to shape deepmirror’s technological framework from its inception and learn in an interdisciplinary environment on the interface of physics, chemistry, biology, and machine learning.

Should I apply? 

We want to be upfront about what it is like to work at deepmirror and thought hard about the principles that guide our work. Before you apply, let's dive into how our values influence the way we work as a team and ensure they resonate with you. 

We Persevere:

We believe that great work comes from dedication, continuous learning, and pushing boundaries. We trust you to manage your time in a way that helps you develop your skills while contributing to impactful projects. If you thrive on learning and enjoy challenging yourself, you'll fit right in. 

We Care 

We love what we do and deeply care about our product, customers, and colleagues. We thrive as a collaborative team where everyone is willing to go the extra mile for our customers. We create an environment where asking for support and extending a helping hand are equally valued. Be part of something big and contribute to a culture of support, customer focus, and shared ambition. 

We Own 

Nobody will dictate how you do things, but you will be held accountable for the impact of your work, as we value outcomes over outputs. If you thrive in an environment where you take responsibility, solve problems proactively, and drive your own success, you will do well here. 

At deepmirror, you will challenge yourself, be supported, and be given the freedom to excel. Join a team where striving, caring, and ownership are not just values but a way of life. If this resonates with you, deepmirror could be your next big adventure—read on for the 'boring' bits. 

In this internship, your primary focus will be on intelligent compound selection for ADMET modelling specifically, how to choose the smallest, most informative set of compounds to measure in order to build predictive models that generalise well across a defined chemical space. The role combines rigorous benchmarking with practical impact, as you develop and evaluate strategies that maximise model performance under realistic experimental budget constraints.

As part of our product-focused team, you will bridge the gap between academic research and industrial applications, translating insights from active learning and cheminformatics into practical guidance for drug development workflows. We maintain a strong commitment to scientific excellence and actively support publication of research findings in peer-reviewed journals.

You will: 

• Design and benchmark compound acquisition strategies, including diversity-based, uncertainty-based, and hybrid active learning approaches
• Evaluate model generalisation across ADMET endpoints in realistic low-data settings
• Investigate how data quality interventions (e.g. removal of activity cliffs, outliers, or noisy datapoints) affect predictive performance
• Publish results in a scientific journal

Requirements

• Strong understanding of cheminformatics and machine learning, with practical experience applying these to real-world problems.
• Experience in Python, RDKit, and PyTorch.
• At the time of internship, you must be enrolled as a Ph.D. student at a University.
• Willingness to work in-person in London for the duration of the internship.

Nice to Have:

• Experience curating and preparing datasets for computational chemistry or ADMET modelling
• Familiarity with active learning methods or Bayesian optimisation
• Familiarity with QSAR/ADMET modelling and molecular property prediction
• Experience working with public chemical databases (ChEMBL, PubChem)

If you meet at least 60% of the requirements or nice-to-have qualifications, we encourage you to apply.

Benefits

• Competitive salary - paid internship
• Social events
• Central London Offices