Biological Engineer 3, AI/Machine Learning

Our mission is to make biology easier to engineer. Ginkgo is constructing, editing, and redesigning the living world in order to answer the globe's growing challenges in health, energy, food, materials, and more. Our bioengineers make use of an in-house automated foundry for designing and building new organisms.

The Protein Engineering Team works to address the complex challenges of protein and enzyme discovery, optimization, and design. We develop, onboard, stress-test, and utilize state-of-the-art protein discovery and design techniques in a continuously improving suite of AI, machine learning, and computational protein design tools. We are responsible for building a platform to "make proteins easier to engineer", and deliver on protein design challenges that span a range of applications from health, agriculture, commodity chemicals, materials, flavors and fragrances, and more.

Ginkgo a large partnership with Google Cloud to build a generative AI platform for engineering biology and for biosecurity. The Protein Engineering team is responsible for delivering best-in-class foundational models and application-specific models to tackle a range of protein design challenges, from generative models for design of enzyme sequences with novel catalytic functions to developing models for significantly accelerating the development of therapeutic proteins.

Specific Role Description

• As a Machine Learning / Artificial Intelligence (ML/AI) Protein Engineer, you will leverage Ginkgo's wealth of proprietary protein data to design, build, and train novel foundational and application-specific (e.g. fine-tuned) AI models for application to protein design and optimization. We have access to nearly limitless compute capacity: CPU, GPU, or TPU. In addition, you will have access to Ginkgo's experimental platform and resulting large datasets for generating and testing hypotheses using machine learning approaches as well as informing strategic training data acquisition.
• We are looking for someone who is excited about the promise of artificial intelligence in synthetic biology and the premier role of biomolecular engineering in biology by design. If you sleep not only to maintain healthy levels of protein in the brain, but also dream of harnessing the power of machine learning and artificial intelligence to design enzymes and other proteins, then you are at the right place.

Responsibilities

• Foundational Model (FM) development: Conceive and develop best-in-class foundational protein language models leveraging Ginkgo's large and diverse proprietary protein datasets. Collaborate in cross-functional teams to design and experiment with model architectures and data schemes.
• Application-specific model development: Conceive and develop purpose-built models (e.g. fine-tuned) for a range of protein design applications leveraging Ginkgo's unprecedented scale of protein experimental data
• Influence strategic dataset acquisition: Partner with world-class experimentalists and hundreds of robots to conceive and design experiments to collect high-value training data at unprecedented scale. Influence how routine experiments are performed to maximize future learning potential.
• Influence the roadmap for AI at Ginkgo: Identify opportunities for application of AI and ML across the company, create prototypes, and contribute to overall prioritization and roadmap development for AI at Ginkgo.
• Take part in something big: This is a growing team, a significant company focus, and a rapidly evolving field. You will be able to influence where things go and how they change.

Minimum Requirements

• PhD in bioengineering, computer science, biophysics, biochemistry, computational biology, bioinformatics, chemical engineering, or related field. May include post doctoral or industry experience. Masters plus 3 years additional postgraduate or industry relevant experience. Bachelors with 5 years additional postgraduate or industry experience.
• Fluency with Python.
• Some exposure with ML and data orchestration and workflow engines like Airflow, Kubeflow, Flyte, or Dagster.
• Familiarity with recent literature and state of the art for large model architectures and training approaches
• Deep knowledge of AI/ML literature as applied to protein science and design
• Experience with building machine/deep learning models with at least one common framework such as PyTorch, Tensorflow, or JAX.

Preferred Capabilities and Experience

• Hands-on experience (1+ years) in developing large foundation models. Deep knowledge of currently available AI model architectures and data schemes. Perspective on advantages and drawbacks of various approaches.
• Broad knowledge of state-of-art machine learning approaches to protein design and biological data analysis
• Fluency in Python. Significant hands-on experience in developing software libraries such as tensorflow, pytorch, jax, keras, and scikit for model construction.
• Expertise in best practices for software development, including version control, code reviews, unit testing, and continuous integration. Experience in ML models management, MLOps, is a plus.
• Knowledge and hands-on experience with physics-based protein modeling and design methods are a plus. Familiarity with at least one type of molecular modeling software such as PyMOL, Rosetta, Schrodinger, Molecular Operating Environment (MOE) a plus. Expertise in the computational modeling of biomacromolecules is a plus.
• Proven track record of delivering in cross-functional teams and in project management. Excellence in scientific communication.
• Enthusiasm to learn new techniques. Strong curiosity of areas of biology previously unknown to you.

Closing

To learn more about Ginkgo, check out some recent press:

Ginkgo, Google Cloud ink AI tie-up with eyes on protein modeling (Fierce Biotech)

Ginkgo teams up with Google Cloud; Two biotechs raise money through private placements (Endpoints News)

Ginkgo Bioworks, Google Cloud Partner on AI, Large Language Models (GenomeWeb)

Ginkgo Bioworks partnering with Google for AI drug discovery (The Boston Globe)

Ginkgo Bioworks CEO: Our AI model will learn to speak DNA just like ChatGPT learned English (CNBC)

What is it really like to take your company public via a SPAC? One Boston biotech shares its journey (Fortune)

Ginkgo Bioworks resizes the definition of going big in biotech, raising $2.5B in a record SPAC deal that weighs in with a whopping $15B-plus valuation (Endpoints News)

Ginkgo Bioworks Redirects Its Biotech Platform to Coronavirus (Wall Street Journal)

The Life Factory: Synthetic Organisms From This $1.4 Billion Startup Will Revolutionize Manufacturing (Forbes)

Can This Company Convince You to Love GMOs? (The Atlantic)

We also feel that it's important to point out the obvious here - there's a serious lack of diversity in our industry, and that needs to change. Our goal is to help drive that change. Ginkgo is deeply committed to diversity, equity, and inclusion in all of its practices, especially when it comes to growing our team. Our culture promotes inclusion and embraces how rewarding it is to work with people from all walks of life.

We're developing a powerful biological engineering platform, so we must remain mindful of the many ways our technology can - and will - impact people around the world. We care about how our platform is used, and having a diverse team to build it gives us the best chance that it's something we'll be proud of as it continues to grow. Therefore, it's critical that we incorporate the diverse voices and visions of all those who play a role in the future of biology.

It is the policy of Ginkgo Bioworks to provide equal employment opportunities to all employees and employment applicants.

Total compensation for this role is market driven, with a starting salary of $minimum of range +, as well as company stock awards. Base pay is ultimately determined based on a candidate's skills, expertise, and experience. We also offer a comprehensive benefits package including medical, dental & vision coverage, health spending accounts, voluntary benefits, leave of absence policies, Employee Assistance Program, 401(k) program with employer contribution, 8 paid holidays in addition to a full-week winter shutdown and unlimited Paid Time Off policy.