Applied Machine Learning Scientist

Variational AI; Vancouver; On-site; CAD 80,000 - 100,000; Full time

Job summary

A pioneering machine learning firm is seeking an applied machine learning scientist in Vancouver or remotely to significantly advance drug discovery through innovative machine learning techniques. The ideal candidate will have strong experience in machine learning methods, particularly deep learning and generative models, with proficiency in Python and PyTorch. A master’s or Ph.D. in related fields is required, alongside at least two years of relevant coding experience. The company promotes a collaborative culture, welcoming applications from diverse backgrounds.

Benefits

Competitive mix of cash and options

Qualifications

• Experience with techniques including diffusion models, Transformers, Bayesian optimization.
• Two or more years of experience developing robust code on larger projects.
• Intellectual curiosity and drive to excel.

Responsibilities

• Run experiments to evaluate new architectures and tune hyperparameters.
• Improve the robustness and efficiency of existing code base.
• Identify, clean, prepare, and test datasets.

Skills

Machine learning techniques

Deep learning

Generative models

Software engineering expertise

Python

PyTorch

Education

M.S. (Ph.D. preferred) in CS, applied mathematics, statistics, physics, or related discipline

Job description

VANCOUVER, BC (OR REMOTE) / 2+ YRS PROFESSIONAL EXPERIENCE

Small molecule drug discovery is one of the most exciting open problems in machine learning. Traditional approaches require over ten years and two billion dollars to develop a new pharmaceutical, and their reliance on trial-and-error calls out for better predictive and generative models. The existent datasets are large enough to benefit from sophisticated deep learning architectures, but small enough that ML models can be trained in a few days, facilitating rapid experimentation and innovation. Nevertheless, the current industry standard has progressed little beyond shallow ML techniques such as random forests and support vector machines, largely due to the difficulty of integrating world‑class machine learning research with chemistry and pharmacology expertise.

Variational AI is searching for an applied machine learning scientist to join us in our quest to radically accelerate the development of new drugs through machine learning excellence. For over six years, we have been advancing the state‑of‑the‑art, and delivering projects to customers including Merck, Rakovina Therapeutics, and ImmVue Therapeutics.

You will help run experiments to evaluate new architectures and tune hyperparameters; continually improve the robustness and efficiency of our existing code base; identify, clean, prepare, and test datasets; and apply our pipeline to new targets, to help develop novel drugs. In this process, you will have the opportunity to build your skills by collaborating with our team of accomplished ML scientists and chemists. Software engineering expertise is required, as well as experience with deep learning and generative models; knowledge of chemistry and pharmacology is preferred but not required.

Here is the background we’re looking for:

• M.S. (Ph.D. preferred) in CS, applied mathematics, statistics, physics, or related discipline;
• Experience with machine learning techniques, including diffusion models, Transformers, and Bayesian optimization, preferably demonstrated through peer-reviewed publications;
• Two or more years of experience developing robust code on larger projects, including code review, refactoring, unit testing, version control, etc.;
• Mastery of Python and PyTorch; and
• Intellectual curiosity and drive to excel.

We are an equal opportunity employer and enthusiastically welcome applications from women, BIPOC, and members of under‑represented communities and groups. Compensation is a competitive mix of cash and options. We prioritize expertise and passion over where you decide to live and work; however, for collaboration across our team, applicants must be based in North American time zones.

To learn more about us, you can find some of our recent work at variationalai.substack.com