Molecular Data Scientist
Reverie Labs (YC W18) is building a pharmaceutical company from the ground up using computation—we’re a drug company that looks and feels like a tech company. We’re a team of engineers and machine learning researchers using cutting-edge tools to design new medicines.
At Reverie Labs, we’re building a pharmaceutical company from the ground up using computation—we’re a biotech company that looks and feels like a tech company.
We’re looking for Molecular Data Scientists to use their interdisciplinary background in chemistry and computer science to build tools, visualizations, and analyses that enable our team to create life-saving cures. At Reverie, Molecular Data Scientists work side-by-side with ML engineers, computational chemists and medicinal chemists to achieve drug discovery objectives. We are looking for mission-driven individuals that are eager to bring ideas from conception to reality.
Do the following sound challenging and fun to you? If so, we’d love to hear from you!
- Using tools like RDKit, Openeye, Amber, and other computational chemistry packages to generate chemical representations that can be used for machine learning.
- Developing Jupyter notebooks to analyze a variety of molecular datasets, using software to extract drug discovery insights like activity cliffs, selectivity hypotheses, and predicted binding modes.
- Combining a set of 25+ in-house experimental assays and 50+ external data streams into a universally accessible data platform.
- Working hand-in-hand with chemists to understand compounds by building tools and visualizations that reflect dataset statistics.
- Developing outlier detection mechanisms to determine whether a data point is likely the result of experimental error.
- Using a modern cloud-first development stack to get access to effectively infinite computing power.
We don’t have a hard set of background requirements, but we highly value skills and experience in the following areas:
- Chemistry-related programming skills: 2+ years experience building tools with widely-used chemistry packages like RDKit, Openeye, etc.
- Visualization: Expert level knowledge of compound and protein visualization tools like PyMol. Non-python tools like R are also valued.
- Statistical knowledge: Knowledge of probability distributions, sampling methods, and other statistics concepts.
- Biotech/Pharmaceutical experience: We are looking for applicants with 3+ years of industry experience or deep technical expertise in an academic setting.
- Applicants with experience and insight from Computational Biology or Genetics are also encouraged to apply.
- Most importantly, an eagerness to learn new skills, wear many hats, and collaborate closely with a growing team of people.
Finally, we base our employment decisions entirely on business needs, job requirements, and qualifications—we do not discriminate based on race, gender, religion, health, parental status, personal beliefs, veteran status, age, or any other status. We have zero tolerance for any kind of discrimination, and we are looking for candidates who share those values. Applications from women and members of underrepresented minority groups are particularly welcomed.
Here’s a small sample of some of the hard tasks we solve to accomplish our goal of developing life-saving treatments for patients:
- Developing new machine learning algorithms and architectures to model complex biological systems.
- Translating state-of-the-art machine learning techniques designed to work on images, text, or audio into the domain of molecules.
- Creating a large-scale distributed training and hyperparameter optimization system.
- Using data mining and processing techniques to uncover new sources of data and clean our existing datasets.
- Using predictive modeling to make critical decisions about which tests to run in the lab.