Deep Origin is a biotechnology company accelerating drug discovery through AI-powered tools. Our platforms simplify R&D, simulate biology, and empower scientists to solve diseases and extend healthspan.

We are looking for an ML Researcher with experience in creating predictive models, particularly in the biology space. You will help to create ML-based representations of specific biological systems, as well as take part in tuning and optimization of larger composite models, with the goal of creating a multiscale biological simulator for drug response prediction. You will also work with the Cellular Simulations team to incorporate biological simulations and mechanistic insights into the ML-based approaches.

Requirements

• B.S. or M.S. in a relevant quantitative field (Computer Science, Math, Physics, etc.).

• At least 2-3 years of experience in the development of machine learning models in an industry setting.
• Knowledge of optimization methodologies for machine learning models.
• Some experience with ML applications in biology.
• Extensive coding experience, preferably Python, but other language proficiency will be considered depending on experience.
• Fluent English for collaboration with an international team.
• Ability to work on US time zones when needed.

Nice to have:

• Ph.D. in relevant field.
• Deep experience in biological modeling and simulation, in particular in a systems biology or molecular level context.
• Experience with ML tasks involving small datasets.
• Experience in optimization of “composite models” - connected models that share output/input.

Responsibilities:

• Construct ML-based representations of biological systems, in particular signaling pathway dynamics in cells
• Help to create a hybrid multiscale biological simulator, incorporating ML components for more effective model calibration and simulation

• Plan and organize work to ensure specific deadlines and milestones are met, coordinating with others to ensure work is correctly aligned and integrated with other efforts. 
• Communicate effectively within the company and external teams, updating others frequently on progress and bottlenecks.