{"@context":"https://schema.org","@type":"JobPosting","title":"Data Scientist H/F
Role details
Job location
Tech stack
Job description
As part of the Rocket Launcher team, you'll play a central role in advancing hit identification, hit expansion, and hittolead efforts. You'll refine and elevate our virtual screening and hitoptimization pipelines, leveraging a multidisciplinary approach to deliver highimpact improvements. You'll partner closely with experts across domains and lead crossfunctional projects that integrate stateoftheart computational technologies into our discovery workflows.
What You'll Be Doing
- Develop, run and evaluate virtual screening pipelines which allow Aqemia to identify promising chemical starting points.
- Develop, run and evaluate hit expansion and hit-to-lead pipelines which allow Aqemia to improve chemical starting points obtained during the phase of virtual screening.
- Contribute to interdisciplinary projects across physics, chemistry, data science, and ML teams.
- Apply in-depth statistical (for instance bayesian optimization) and exploratory research data analyses to improve pipeline performance.
- Contribute to identify technical gaps and develop custom solutions.
- Stay current on scientific literature and recommend improvements in virtual screening and hit optimization.
(Note: This position does not involve deep learning methods development.)
Requirements
MSc (at least 3 years of experience after MSc) or PhD in Data Science, Statistics, Computer Science, or related fields.
- You are proficient in python or other object-oriented programming languages.
- Proven experience in scientific data analysis, ideally in life sciences.
- Proven understanding of statistical methods and exploratory research data analysis.
- You have excellent written and verbal communication skills, paired with a strong intellectual curiosity and the ability to quickly absorb new frameworks.
Nice-to-Have:
- Bayesian optimization is a plus.
- Experience with Cloud technologies is a plus.
- Experience with large datasets is a plus.