Senior Data Scientist, NGS

Key Skills

Java Programming, Python Programming, C++, C Programming, SQL, Cloud computing, Scala Programming, Machine learning techniques, Data science techniques, MATLAB Programming, PyTorch, TensorFlow, R Programming

Job Description

We created 13 petabytes of fit-for-purpose biological data. Want to work with it?

When combined with the right algorithms, data can do amazing things: it can encourage strangers to buy something or to click an ad, it can suggest a video or what word might want to use next. Those problems are clearly challenging and interesting, but why not use data science to tackle problems that have plagued humanity for generations: to revolutionize how we recognize and treat disease to directly improve lives and reduce suffering?

Wouldn't that be a career you could be proud of?

Recursion leverages sophisticated machine-learning algorithms to distill from its dataset the Recursion Map, a collection of hundreds of billions of searchable inferences across biology and chemistry unconstrained by human bias. As a data scientist at Recursion, you can make an even greater impact on human health and impact more lives than physicians treating one patient at a time. Data scientists at Recursion do science: from designing well-controlled experiments to building models and interpreting results, your skill and expertise can help us infer new compounds and treatments for diseases impacting people around the world.

Beyond the obvious impact you could make, Recursion is designed for data scientists. You will be a part of a team of 30+ data scientists managing 13 petabytes of data, all generated internally and to our specifications’ specifications in an automated lab mere feet from where you work. Beyond scale, the secret sauce is that the data lives as a relatable dataset, fit-for-purpose directly answering complex experimental research questions.

Our mission is to decode biology to radically improve lives by industrializing drug discovery. This includes building the most scalable drug discovery platform in the history of the BioPharma industry with a combination of biological and laboratory expertise, automation engineering, and cutting-edge computational tools. To this end, we have generated and continue to grow one of the largest biological datasets in existence in our labs—images of billions of cells under millions of biological and chemical perturbations, and a growing dataset of transcriptional profiles generated by next-generation sequencing.

It is an audacious goal, but it isn’t a dream or science fiction. ??It’s something we’re already doing.

The Impact You'll Make

With treatments for hundreds of diseases in our sights, we’ve built a data science team with domain expertise in computer science, bioinformatics, physics, biology, mathematics, applied statistics, and more. We work side-by-side with biologists, automation scientists, chemists, software engineers, and many others; together, we develop the tools and methods to turn our experimental data into treatments for pathologies that affect the lives of countless individuals.

In this role, you will be a computational and analytical expert who develops scalable NGS solutions that impact our drug discovery pipeline. You will be working side-by-side with colleagues with complementary expertise.

• Strategize in collaboration with biologists, engineers, and data/ML scientists on the next steps for leveraging NGS data to industrialize various stages of the drug discovery process.
• Deliver scalable software tools for the evaluation and communication of NGS data generated by Recursion’s high-dimensional, high-throughput transcriptomics assay platform.
• Design scalable NGS and multi-modal analysis tools that will be integrated into the Recursion platform. These tools will enable rapid improvements to our inference-based drug discovery pipeline and accelerate the overall drug discovery process.
• Develop visualization tools to aid biologists in the interpretation of phenotypic and transcriptomic relationships observed in our internally generated data.

The Team You’ll Join

Our team’s mission is to develop and scale a transcriptomics (RNAseq) assay to complement our imaging platform, and apply the data toward accelerating drug discovery at Recursion. This will be the second largest high-throughput assay at Recursion after our imaging platform, and this team is tasked with developing it from proof of concept through launch and operation of an industrialized high-throughput assay available across the organization. You will be joining a fast-growing, cross-functional team with expertise in biology, automation engineering, data science, software engineering, and product development with a specific focus on NGS assay development and application. You can expect to be challenged with new scientific domains, high expectations for analytical software development, unresolved questions about analytical methods and applications, and ambitious goals to industrialize and scale various aspects of the drug discovery process. A bold, collaborative, growth-oriented, and team-first mindset will be critical to the success of both individuals and teams in this exceptionally challenging and exciting industry.

The Experience You’ll Need

• A firm grasp of the fundamentals of probability, statistics, and machine learning.
• Direct experience analyzing next-generation sequencing (NGS) transcriptomics datasets.
• High fluency with the Python data stack (numpy, pandas, scikit-learn, etc).
• Experience with collaborative software development and peer code review, including version control tools like git.
• Experience developing, releasing, and maintaining software in a continuous-use production environment.
• A track record of outstanding past projects, product development, publications, or presentations.
• 3+ years postdoctoral experience in industry or academia on directly relevant subjects, and/or experience as a technical lead driving execution in these areas.
• Preferred: direct experience in using NGS datasets developing assays for a production environment