Data scientist / ML

We have 30 years of expertise in designing and building custom software systems. We provide software development services focusing on complex high-load applications, AI and BI solutions, and mobile apps.

Project description: Project about virtual progressability series analysis.
The goal is to improve hit triaging process in early chemisty.
To do this, you will be working on improving ADME models through active learning by means of interacting with human scientist.
You will also be working on algorithms that will be used to rank chemical series.
A single analysis will contain up to 100K compounds.
The scope of work will include work on improvement of existing ML models, training of new models and automation of ML pipelines.
Analysis functionality will be integrated with existing molecular design and data-driven decision making solutions.
This most likely will require developement of simple Streamlit/Dash application.

Required skills

• Strong Python (4+ years of experience).
• Relevant ML experience: AI/ML model building and analysis (GNNs, RF, GPs, LGBM, etc):
    - experience working with small datasets, imbalanced datasets;
    - experience with PyTorch;
    - active learning;
    - uncertainty quantification.
• Experience with Docker.

Would be a plus

• Experience in chemistry domain.
• Experience working with RDKit or other chem packages.
• Experience with Bayesian optimization.
• Experience with Airflow, Flute, Kubernetes.
• Experience with Streamlit/Dash.

Our offer as your future employer

• Collaboration via a B2B contract with payments in EUR or USD, depending on your preference, or through a labor contract if you are based in Georgia, Serbia, or Kazakhstan.
• Flexible work schedule.
• Possibility to work remotely (excluding Russia and Belarus).
• Opportunities for professional growth.
• A company laptop to ensure a comfortable and efficient work setup.

​​​​​