Scientist II, Machine Learning

About Generate:Biomedicines

Generate:Biomedicines is a new kind of therapeutics company – existing at the intersection of machine learning, biological engineering, and medicine – pioneering Generative Biology™ to create breakthrough medicines where novel therapeutics are computationally generated, instead of being discovered. The Company has built a machine learning-powered biomedicines platform with the potential to generate new drugs across a wide range of biologic modalities. This platform represents a potentially fundamental shift in what is possible in the field of biotherapeutic development.

We pursue this audacious vision because we believe in the unique and revolutionary power of generative biology to radically transform the lives of billions, with an outsized opportunity for patients in need. We are seeking collaborative, relentless problem solvers that share our passion for impact to join us!

Generate:Biomedicines was founded in 2018 by Flagship Pioneering and has received over $700 million in funding, providing the resources to rapidly scale the organization. The Company has offices in Somerville and Andover, Massachusetts with 300+ employees.

The Role: 

The data science team at Generate builds, extends, and maintains the technology we use to drive model-based optimization of proteins. We curate internal and external data, train and develop models that predict different protein properties, formulate fit-to-purpose optimization algorithms, and build tools that supercharge our protein designers. We collaborate broadly with experimental and computational teams across the company to ensure that we are making the best use of Generate wet lab and ML capabilities to efficiently explore molecular space and create new therapeutics.

We are seeking creative, motivated, and rigorous Machine Learning Scientists to contribute broadly to our core technology stack. We are especially keen to find a teammate with a builder’s mentality, someone who is eager to drive technology development all the way from ideation and algorithm R&D to software design and testing. They will join a vibrant group of computational scientists working on a variety of challenging and impactful problems that touch just about every aspect of the Generate tech stack. They will work with our engineering teams and protein designers to ensure that R&D gets seamlessly integrated with and deployed on our protein design platform.

Here's how you will contribute:

• Train and develop large scale protein foundation models for use in protein property prediction
• Design and test new methods for supervised learning of protein properties
• Contribute to applications of BayesOpt tech throughout Generate, from protein design and model hyperparameter tuning to assay optimization
• Implement and adapt models and algorithms from the literature
• Design and build unit-tested and performant ML library code and tooling that powers different capabilities in our platform
• Work with Engineering teams to deploy production-grade ML systems
• Keep up-to-date with the latest developments in applied ML and protein ML
• Present in regular research meetings and prepare content for internal and external communication across multiple disciplinary boundaries
• See your contributions to our tech stack result in proteins that get characterized in the wet lab and help advance life-changing therapeutic programs

The Ideal Candidate will have:

• PhD in Computational Biology, Computer Science, or a related field with a track record of innovative ML method development for scientific applications
• 3+ years of experience with developing ML methods to solve scientific problems, with a particular focus on applications to protein modeling or adjacent fields such as genomics, chemistry, or physics
• Experience developing, debugging, and scaling models using modern deep learning frameworks such as PyTorch or JAX
• Advanced proficiency in Python and experience analyzing scientific data with Numpy/Scipy/Pandas.
• Demonstrated experience developing high-quality, unit-tested software in a team setting.

Nice to have:

• Domain expertise around protein design, biochemistry, genetics, biophysics, and/or chemistry as well as practical experience working with data in these domains
• Foundational knowledge of probabilistic ML, including Bayesian Optimization
• Experience building systems that employ LLMs, e.g. LLM agents
• Publications at major scientific venues such as ML conferences or scientific journals that advance ML methods or apply ML to hard problems in the biological and physical sciences

Generate:Biomedicines is committed to equal employment opportunity regardless of race, color, ancestry, religion, sex, national origin, sexual orientation, age, citizenship, marital status, disability, gender identity or Veteran status.

COVID Safety:

Generate:Biomedicines enforces a mandatory vaccination policy for COVID-19. All employees must be fully vaccinated and have received a booster.  The purpose of this policy is to safeguard the health of our employees, their families, and the community at large from infectious disease that may be reduced by vaccinations.  The Company will make exceptions to this policy if required by applicable law and will consider requests for an exemption from this policy due to a medical reason, or because of a sincerely held religious belief, or any other exemptions that may be recognized by applicable.

Recruitment & Staffing Agencies: Generate:Biomedicines does not accept unsolicited resumes from any source other than candidates. The submission of unsolicited resumes by recruitment or staffing agencies to Generate:Biomedicines or its employees is strictly prohibited unless contacted directly by the Company’s internal Talent Acquisition team. Any resume submitted by an agency in the absence of a signed agreement will automatically become the property of Generate:Biomedicines and the Company will not owe any referral or other fees with respect thereto.