Artificial intelligence for drug discovery.

Senior Machine Learning Engineer

San Francisco
Job Type
Apply to Atomwise and hundreds of other fast-growing YC startups with a single profile.
Apply to role ›

About the role

Atomwise is the leading artificial intelligence (AI) drug discovery company, based in San Francisco, CA. We discover and develop small molecules that will improve human health and agricultural productivity. 

Every day we're breaking new ground in developing and applying leading-edge machine learning methods to pre-clinical drug development. This is an opportunity to apply your skills (and learn new ones!) at the intersection of chemical/biological sciences, data science, machine learning, and software development. 

We are looking for a senior machine learning engineer with model development and evaluations skills to join our ml.research team. This team is responsible for developing new ideas and techniques used by our applied researchers, cheminformaticians, and production scientists. As part of our team, you work on problems related to:

  • Out-of-distribution, imbalanced, and noisy data: Our training data is seldom i.i.d.; new medicines are unlocked by pushing out into newly-discovered biology. Classes are extremely unbalanced, ratios of 1 positive to 70,000 negatives are typical. Help us reason about how to learn appropriately without dismissing nor overfitting to the data; identify when we can trust a label or have confidence in a prediction; and develop techniques to find and correct for systemic biases.
  • Self-supervised learning and latent representations: To get the most out of our labeled data, we are leveraging large datasets of unlabeled data. Help us use self-supervised learning algorithms to learn optimal representations of bioactivity data.
  • Cutting-edge network architectures: We are constantly exploring deep learning architectures, including graph neural networks, transformers, and equivariant neural networks. Help us follow the literature, and develop new network architectures.
  • Underspecification and stress testing: At Atomwise, our informal motto is "Don't fool yourself." While we believe in the power of machine learning, we strive to maintain a healthy skepticism of its limits. Help us imagine new and interesting ways to stress-test our existing models, and ensure they will do what we want in real-world scenarios. 

Our Machine Learning team is small and growing quickly. As a result, there are plenty of opportunities to have a big impact on our success.

Required qualifications:

  • Ph.D. or M.Sc. in computer science, statistics, data science, or related field
  • 5+ years of extensive practical experience and proven track record of developing, implementing, debugging, and extending machine learning algorithm
  • Knowledge of modern neural network frameworks such as PyTorch, TensorFlow, or JAX
  • Strong analytical and statistical skills
  • Scientific rigor, healthy skepticism, and detail-orientation in training and analyzing machine learning models
  • Familiarity with processing large data sets in a Linux environment

Preferred qualifications:

  • Software engineering skills and coding experience in at least one high-level programming language (Python, R, Java, C/C++, etc.)
  • Biomedical knowledge or experience in processing chemical or biological data is preferred but not required
  • Experience with cloud computing environments (AWS/Azure/GCE)

Please apply with a resume and cover letter.

Compensation and Benefits:

  • Great, world-class team of colleagues – scientists from a variety of backgrounds (chemistry, medicine, biology, physics, CS/ML)
  • Stock compensation plan – you’ll be an Atomwise co-owner
  • Platinum health, dental, and vision benefits
  • 401k with 4% match
  • Funding for professional development and conference attendance
  • Flexible work schedule
  • Generous parental leave

Atomwise is an equal opportunity employer and strives to foster an inclusive workplace.  Our mission is to develop better medicines faster, and we know that we need a diverse team to develop medicines that serve diverse populations.  Accordingly, Atomwise does not make any employment decisions (including but not limited to, hiring, compensation, and promotions) on the basis of race, religion, color, national origin, gender, gender identity, sexual orientation, age, veteran status, disability status, or any other characteristics protected by applicable federal, state, and local law.

We strongly encourage people of diverse backgrounds and perspectives to apply.

Atomwise is not currently offering visa sponsorships for any position. Please only apply if eligible to work in the U.S.

Pursuant to the San Francisco Fair Chance Ordinance, we will consider for employment qualified applicants with arrest and conviction records.


Why you should join Atomwise

Atomwise Inc. patented the first deep learning technology for structure-based small molecule drug discovery. This AI technology harnesses millions of data points and thousands of protein structures to solve problems that a human chemist would take many lifetimes to solve. Atomwise has partnered with some of the world's largest pharmaceutical and agtech companies and with more than 100 leading academic institutions and hospitals, to tackle the challenges of discovering and developing better drugs and agrochemicals. Atomwise has raised over $50 million from leading venture capital firms to support the development and application of its AI technology.

Team Size:50
Location:San Francisco
Abraham Heifets
Abraham Heifets
Izhar Wallach
Izhar Wallach