Overview
The successful candidate will be a Ph.D. level data scientist with knowledge in the life sciences, including protein structures, small compound analytics and broader LS/HC subject matter. The candidate will also be able to develop deep learning applications using Python as a primary tool, both to implement novel solutions and iterate on existing software solutions. The candidate will primarily work in a virtually distributed, dynamic and extensively experienced technical team.
Responsibilities
Responsibilities for the Data Scientist will include:
- Work closely with other data scientists and SMEs to develop DL/ML powered software features
- Support projects through the data science lifecycle - from R&D to production
- Carry out preprocessing of structured and unstructured data
- Processing, cleansing, and validating the integrity of data to be used for analysis
- Devise and collect data on metrics surrounding the success of the systems developed by Vyasa
Qualifications
The ideal candidates will have the following skills or experience:
- Exceptional Python skills, experience using scientific libraries including Tensorflow/Pytorch to train and serve models for inference
- Familiarity with containerization tools such as Docker/Kubernetes
- Ability to work in a distributed, fast-paced software environment with minimal supervision
- Familiarity with CI/CD and version control tools, unit/integration testing, working with Git
- Extensive knowledge of deep learning and machine learning techniques, and pitfalls, and experience applying them to real world data sets
- Comfortable working in a remote environment and communicating via chat, video conference, screen sharing and phone calls