COMPANY OVERVIEW:

At 1859, we are creating a pico-scale HTS platform (pico-HTS) that enables us to test millions of small molecule potential medicines in a single day and at an exponentially lower cost point compared to conventional HTS. At scale, our technology has the potential to usher in the promise of precision medicine and democratize the medicine discovery process. At 1859, we are committed to scientific integrity, discipline, objectivity, and openness. Our team consists of very talented chemists, assay biologists, material scientists, integration engineers, automation specialists and informaticians working closely together to bring our screening technology to the world.

We are comprised of high-performance engines, not cogs, and we invest in our people! Benefits include: paid holidays, PTO, a variety of medical plans, dental and vision insurance, a 401(k) plan, employee recognition awards, happy hours, company activities, and equity incentives. We are committed to training and career development for our people. Our goal is to provide a collaborative, data driven, productive and highly efficient company culture.

If you have a passion for changing the world of new medicine discovery, we encourage you to apply!

POSITION SUMMARY:

We are looking for a Machine Learning Scientist to join our Data Informatics Team. The team designs and implements deep learning and AI architectures, as well as the software that supports our library design, hit selection, hit-to-lead and lead optimization pipeline.

KEY RESPONSIBILITIES:

• Collecting, curating, and analyzing bioactivity and ADMET data from internal screening programs and public and commercial sources

• Designing, identifying, implementing, and validating machine/deep learning and AI model architectures and tools

• Using models to design libraries for a diverse set of protein-targets across different disease areas

• Communicating results to internal and external stakeholders 

• Building an automated pipeline to refresh existing models with new data

• Building dashboards that monitor model predictive performance over time

REQUIREMENTS:

• PhD in Computer Science, Mathematics, Statistics, Computational Chemistry/Physics, or a related quantitative discipline

• 2+ years of relevant experience

• Expert applied machine learning skills, demonstrated by a strong publication record at leading conferences, journals, or other substantial contributions to the field

• Solid analytical and statistical skills

• Scientific rigor, healthy skepticism, and detail-oriented in developing and analyzing machine learning models

• Expert knowledge of the Python machine learning frameworks, e.g., Scikit-learn, PyTorch or TensorFlow

• Comfortable with Linux command-line environment

• Pro-active team player and creative problem solver

HIGHLY DESIRABLE:

Experience with one or more areas of geometric deep learning, including generative models, and reinforcement learning

Familiarity with open challenges in AI-driven drug discovery

Experience with:

• DEL-based HTS

• Cloud computing environments (AWS/Azure/GCE)

• Creating scalable methods that utilize vast amounts of data

Ability to deliver production-quality code; experience with code review

_ _

_ _

We take pride in fostering an environment where all team members are afforded the freedom to pursue their passion without regard to race, color, religion, national or ethnic origin, gender, sexual orientation, gender identity or expression, age, disability, veteran status or any other characteristics protected by law.