Machine Learning Engineer at OneThree Biotech in NYC

More about us:

Currently developing a single new drug can take over $1B and 15 years, with over 99% of drugs failing along the way. This is why over 70% of all known diseases have no treatments and millions of patients are left with no viable treatment options.

At OneThree Biotech we’re working to change this using biology-driven AI. Founded after members of our team lost family members to rare cancer, the team at OneThree has spent the last 5+ years researching how we can combine AI with systems biology to stop this from happening to anyone else. We’re building a platform to not only predict new potential therapeutics, but also to pinpoint the mechanisms driving efficacy, and we pride ourselves on building a new form of biology-driven AI that values interpretability as much as accuracy. After raising a multi-million round of funding, we’re looking for a Machine Learning Scientist to join our interdisciplinary team as we look to ramp up external partnerships and internal development.

About the Role:

You will work closely with our Chief Data Scientist and our research and engineering teams to both improve existing algorithms and develop new machine learning approaches for a variety of unsolved biological questions. The ideal candidate will be interested in diving into machine learning beyond just an AUC or accuracy and will seek to truly build interpretable methods. The ideal candidate will have an entrepreneurial mindset, be comfortable with creative problem solving, and be comfortable collaborating with interdisciplinary teams. This is a rare opportunity to get in at the early stage and take ownership over product and strategy. If working on challenging problems that could have a real positive impact if solved excites you, then maybe OneThree is the place for you!

Responsibilities:

• Work closely with computational biologists to apply cutting edge machine

learning algorithms and approaches to drug development

• Build models that prioritize interpretability as well as model performance

to ensure the highest level of biological understanding

• Apply advanced feature selection and engineering techniques to data

pre-processing

Requirements:

• PhD in a quantitative subject (Masters + 2 years work experience also

acceptable)

• Expertise implementing a variety of machine learning techniques (e.g.

SVM, Random Forest, neural networks)

• Working knowledge of scripting languages, Python strongly preferred

• Experience with traditional machine learning packages, such as sklearn, numpy, pandas (plus: keras, tensorflow)

• Experience with relational databased (PostgreSQL preferred)

• Experience using AWS (RDS, Sagemaker, etc)

Nice To Have:

• Experience working with un-structured data, transfer learning, and/or

Natural Language Processing

• Any experience in life science, health or biotech

• Publication track record (pre-prints count!)

Benefits:

• Comprehensive Healthcare, Dental, and Vision

• 25 days PTO (inclusive of 2 companywide weeks off)

• 401K

• Flexible work environment

• Office at the exclusive Grand Central Tech hub, directly across from

Grand Central Station

• Free coffee, nitro cold brew, tea, and work events

• Monthly team snack budget

• Private access to a large terrace with Manhattan views

• Subsidized cafeteria for lunch

• Early access to Bergamo’s before opening hours