Aqemia is an in silico drug discovery start-up, whose ambition is to discover rapidly more innovative therapeutic molecules with better chances of success. How? Just like an AI can learn to play chess, Aqemia’s generative AI learns to invent relevant compounds thanks to unique Statistical Mechanics algorithms predicting drug-target affinity among other properties. Aqemia’s differentiation lies in its affinity prediction both accurate and 10 000x faster than competition, enabling efficient guidance of generation towards compounds with better chances to become drugs.
Aqemia is a spin-off of the École Normale Supérieure Paris leveraging disruptive algorithms from 8 years of research. Aqemia’s team is composed of a dozen of high profiles at the crossroads of Medicinal Chemistry, Statistical Mechanics and Artificial Intelligence. Founded in June 2019, we have raised €1.6M with leading VC fund Elaia Partners, Bpifrance and business angels. Our office is located in the center of Paris at Agoranov, a top-notch deeptech incubator.
We’re looking for a
Research Intern - Machine Learning and Deep Learning
to join our core team and make an impact on a critical challenge: discovering drug candidates to cure key diseases. You will work in an interdisciplinary team of medicinal chemists, physicists and ML engineers.
If this sounds exciting to you, come and join us!
As a research intern, you will explore in depth a particular topic, all the way from literature review to testing your approach on proprietary data. We are willing to discuss the choice of the topic so that it best fits your expertise, but it could include :
- Generation of molecules in a constrained chemical space.
- Development of interpretable predictors of molecular properties.
- Multi Constraint Optimization strategies to generate molecules that satisfy several criteria.
- Representation learning on molecules : unsupervised or semi-supervised techniques to learn embeddings of molecules.
- Active learning strategies to decide when to acquire new data or to use model prediction.
- You are a Masters student in Computer Science or applied mathematics.
- Ideally with hands-on experience in representation learning, generative models, reinforcement learning.
- Interest for complex data such as graphs, text, 3D objects / point-clouds.
- Interest for unsupervised learning, low-data tasks and active learning.
- With experience in reading academic papers and exercising critical thinking on results.
Nice to have:
- Basic knowledge in biology and chemistry is a strong plus, but it is not required.
You should join us if…
- You are passionate about solving difficult problems on topics that really matter
- You are curious, willingful and dynamic
- You like working collaboratively in an interdisciplinary, fast-paced environment
- You want to join a small team to bring your own impact in drug discovery
To apply, send us your CV at firstname.lastname@example.org.