Recursion is a digital biology company industrializing drug discovery. We are working to solve some of the hardest, most meaningful problems facing human health today. Come join us in our mission to decode biology to radically improve lives, while doing the most impactful work of your life.
The Impact You’ll Make
You are an engineer with experience building models on text or graphs on massive datasets. On the Digital Chemistry team the models we produce will decide the next set molecules to be synthesized and tested against biology. We need someone who is passionate about building ML systems the right way, and who is excited about dealing with new modalities of data to solve meaningful problems that will literally save lives.
We do not expect you to be an expert in biology, chemistry or pharmaceuticals; We have those already, we need someone with a desire to learn from and work with our diverse group, and bring the best ML engineering practices to help us build models over billions or trillions of potential molecules.
- You'll implement baseline models and pipelines to train models on molecular structures and our own internal datasets
- You'll design multimodal FeatureStores for quickly serving molecules in many representations (SMILES strings, graphs, 3D) to our neural networks during training
- You'll build fast inference, ranking and indexing systems to help choose the next molecules to synthesize
- You'll build systems to empower our discovery teams (biologists, chemists, and data scientists) to generate small molecule leads for disease programs using the output of these models
- You'll present publishable work at top machine learning and computational chemistry conferences
The Team You’ll Join
As a member of the Digital Chemistry team, you'll join other scientists at Recursion in applying machine learning techniques to drug discovery problems. You'll collaborate on cross-functional teams and participate in diverse working groups as you positively impact Recursion's ability to improve human lives.
The Experience You’ll Need
- 2+ years of experience building large-scale ML systems
- Experience releasing and maintaining deep learning-based products in a continuous-use production environment
- Experience working in a collaborative CI/CD software development environment, including use of git, peer code review and independent authorship of well tested, easily maintained, scalable, and documented code
- Experience using modern technologies to accelerate machine learning. We use Python, PyTorch, and PyData libraries. We have our own on-premise GPU cluster and distributed file system, as well as access to ample cloud resources
- Computational chemistry experience is helpful but not necessary, instead you are open and interested in learning chemistry and able to work with chemists and biologists to understand how to make useful tools for them
The Benefits/Perks You’ll Enjoy
- 100% Coverage of health, vision, and dental insurance premiums
- 401(k) with generous matching (immediate vesting)
- Stock option grants
- Two one-week paid company closures (summer and winter)
- Flexible vacation/sick leave
- Generous paid parental leave (including adoptive)
- Onsite daycare facility*
- Commuter benefit and vehicle parking to ease your commute*
- Complimentary chef-prepared lunches and well-stocked snack bars*
- Monthly fitness/wellness stipend
- One-of-a-kind 100,000 square foot headquarters complete with a 70-foot climbing wall, showers, lockers, and bike parking*
*Subject to change for remote-based employees during the COVID-19 pandemic. These benefits are specific for HQ-based employees.