X is Alphabet’s moonshot factory. We are a diverse group of inventors and entrepreneurs who build and launch technologies that aim to improve the lives of millions, even billions, of people. Our goal: 10x impact on the world’s most intractable problems, not just 10% improvement. We approach projects that have the aspiration and riskiness of research with the speed and ambition of a startup.

About the team

We are multidisciplinary scientists and engineers dedicated to creating transformative computational tools for Synthetic Biology. Our moonshot is to accelerate discovery and bio-innovation for healthier people and a healthier planet. 

About the role

We’re looking for a machine learning scientist/engineer to work with our computational biologists and experimentalists on data-driven methods for the design and optimization of proteins. Our goal is to radically improve the state of the art in applied protein engineering by developing new computational methods and applying recent advances such as AlphaFold and protein LLMs. This role combines modern engineering, foundational machine learning work, and biologically-motivated design, and is central to the team’s impact.  We are looking for someone that’s passionate about applying ML on real world problems, not SOTA chasing on public benchmarks.

The ideal team member will demonstrate scrappiness, creativity, and drive to “make it happen” by iterating rapidly and adapting state-of-the-art methods to team and customer needs. This teammate will help us keep our finger on the pulse of the real-world by ensuring we are continually adding value to our customers. They will thrive in an organization that rapidly iterates, evolves, and leans into ambiguity.

How you will make 10x impact

• Identify, track, and summarize developments in the field of machine learning applied to protein function discovery and enzyme design, through literature reviews, evaluations, and adaptations of known and new methods to the team's needs and goals
• Develop novel methods for applying machine learning at scale to custom data sets, to model and predict protein structure, function, and properties. Propose, design, and implement models for optimizing biomolecular sequences for enzyme functions such as folding and secretion
• Achieve the best results in domains with scarce data: finetuning foundation models, leveraging active learning for optimal experiment designs, or figure out how to combine literature data with new experiments
• Understand customer needs, data, and metrics, and translate them into joint work with scientists, engineers, and experimentalists on the team. Play a central role in informing and prioritizing new product features and team emphasis
• Make business recommendations with effective presentations of findings/insights to stakeholders at various levels, as well as to external partners

What you should have

• PhD degree in a relevant field (Computer Science, Bioinformatics, Computational Biology) or equivalent practical experience
• Deep expertise in modern neural network architectures such as transformers, VAE, energy based models
• Experience with state-of-the-art machine learning approaches applied to biological sequence data (RNA, DNA, proteins) in the molecular and cell biology domains
• Experience with general-purpose programming languages (preferably Python) in a production environment. Comfort with modern software engineering practices such as version control, code reviews, unit testing, and continuous integration
• Familiarity with modern deep learning frameworks such as JAX, Pytorch and Tensorflow
• Excellent communication skills and aptitude for working with cross-functional teams

 It’d be great if you also had these

• Experience working with or evaluating deep neural networks applied to protein prediction tasks.  For example: using LORA for foundation model fine-tuning, or, leveraging domain adaptation for handling batch effects from noisy heterogeneous data
• Experience with additional data-driven tasks in biochemistry, such as metabolic engineering or genomics
• Industry experience in small teams building solutions in the molecular biology domain
• Experience with Bayesian search or active learning approaches for optimal experiment design
• Excellent communication and project management skills, with a track record of handling multiple customers and streams of work

The US base salary range for this full-time position is $157,000 - $243,000 + bonus + equity + benefits. Our salary ranges are determined by role, level, and location. Within the range, individual pay is determined by work location and additional factors, including job-related skills, experience, and relevant education or training. Your recruiter can share more about the specific salary range for your location during the hiring process.

Please note that the compensation details listed in US role postings reflect the base salary only, and do not include bonus, equity, or benefits.