Data Scientist / Protein Design

Key Skills

Automation, Data science techniques, Data structuring, Effective communication skills, Machine learning techniques, Python Programming, PyTorch, TensorFlow

Job Description

Team

Software Engineering | Automation Engineering | Finance & Operations | Machine Learning | Research & Development | Product Management

Aether's Machine Learning (ML) team is spearheading innovation in the field of enzyme engineering by capitalizing on advanced computational methodologies. Faced with the intricate and multidimensional challenges of enzyme engineering, the ML team employs a suite of refined data-cleaning algorithms to meticulously curate and preprocess extensive volumes of experimental data. By deploying state-of-the-art predictive models, the team has the capability to accurately predict enzyme-substrate interactions, uncover novel enzymatic activities, and optimize enzyme performance across diverse experimental conditions. Furthermore, by utilizing cutting-edge multi-objective search and optimization algorithms, the ML team can concurrently navigate multiple solution spaces, adeptly navigating trade-offs between conflicting objectives to engineer optimal enzyme designs. Aether's innovative fusion of data science and biotechnology is facilitating the creation of pioneering solutions that address pressing challenges within the biotech industry and unleash the boundless potential of enzymes for a wide array of applications.

Opportunity

We are seeking an experienced and highly motivated Data Scientist to join our ML team and contribute to the cutting-edge field of protein and enzyme design. In this role, you will be responsible for developing novel machine learning models, particularly diffusion models and latent language models (LLMs), to advance the design and engineering of proteins and enzymes. Your work will play a pivotal role in driving the innovation and success of our enzyme engineering projects.

Job Responsibilities:

• Development and implementation of diffusion models for enzyme design
• Development and implementation of LLM-based machine learning models for enzyme design.
• Collaboration with cross-functional teams, including chemists, biochemists, and data scientists.
• Analysis and interpretation of experimental data to validate and refine machine learning models.
• Development and maintenance of software tools and pipelines to support data analysis, model training, and model deployment.
• Presentation of research findings, model performance, and insights to internal teams and external collaborators.
• Staying current with advances in machine learning, computational biology, and protein engineering to inform model development and improvement.
• Contributing to the preparation of scientific publications, technical reports, and patent applications.
• Building internal tools for research teams to interpret and categorize data generated by protein and enzyme engineering experiments.

You will BRING to this role:

• Ph.D. in Computational Biology, Mathematics, Computer Science, or a related field.
• Strong understanding of protein structure, function, and biochemistry.
• Proven experience developing and applying machine learning models, particularly diffusion models and LLMs, in a biological or biochemical context.
• Proficiency in Python and experience with machine learning frameworks such as TensorFlow, jax or PyTorch.
• Strong problem-solving and critical-thinking skills, with a high level of attention to detail.
• The challenges of a startup excite you. Aether Biomachines is changing the world through a platform that has the potential to revolutionize humanity’s relationship to manufacturing. Our ability to build and maintain scalable and efficient systems to deliver a continuously improving product will be the main differentiator between the success and failure of the organization, and you will be a key stakeholder in this process. You believe you are up to the task and want to prove it.

What to expect:

• Month One:
• Gain a solid understanding of Aether's workflows, data structures, and machine learning pipelines.
• Gather requirements from ML and R&D teams for developing diffusion models and LLMs for protein and enzyme design.
• Begin development of machine learning models for protein and enzyme engineering.
• Three Months:
• Refine and validate machine learning models based on experimental data and feedback from the R&D teams.
• Collaborate with R&D teams to apply predictive models to ongoing protein and enzyme engineering projects.
• Present preliminary model performance results to internal stakeholders.
• Six Months
• Fully integrate machine learning models into Aether's protein and enzyme engineering workflows.
• Continue to improve and expand the capabilities of diffusion models and LLMs for protein and enzyme design.
• Support ongoing projects and contribute to the advancement of Aether's enzyme engineering endeavors.

Life at Aether:

• Full suite of health benefits (medical, dental, vision)
• Ancillary benefits, including 401(k), HSA/FSA programs
• Commuter Benefits: Aether will match up to $100/month (Commuter benefits can be allocated towards commute expenses, parking expenses, or both)
• Learning & Development: You may purchase up to $50/month in books or other learning materials without any prior approval
• Access to the gym at our Menlo Park location
• Access to our Menlo Park Labs Shuttle & Parking
• Unlimited PTO and 10 Paid Company Holidays
• Stocked snack cabinet and monthly team bagel breakfast
• Flexible work schedule to accommodate you/your family needs
• Quarterly company-wide events and activities
• Fun--and useful--swag!

EEO

Our company values diversity and believes diverse teams make innovation possible. We work on complex, difficult problems with no linear or clear solutions. We believe that a diverse team can bring different perspectives and approaches, and whose experiences reflect the full set of clients we seek to serve. As such, Aether Biomachines, Inc. is committed to a diverse representation among our employees. Legal authorization to work in the U.S. is required. Aether Bio may agree to sponsor an individual for an employment visa now or in the future if there is a shortage of individuals with particular skills for this job. In compliance with federal law, all persons hired will be required to verify identity and eligibility to work in the United States and to complete the required employment eligibility verification form upon hire. This position is based in our California location.

This is the pay range for this position that we reasonably expect to pay. Individual compensation is based on various factors, including experience, education, skillset, and geographic location. This range is for the SF Bay Area, California location, and may be adjusted to the labor market in other geographic areas.

SF Bay Area Pay Range

• $157,500—$192,500 USD