The Chan Zuckerberg Initiative (CZI) aims to solve society's toughest challenges, including eradicating disease by the end of the century. To achieve this, CZI needs to build an AI-based virtual cell model and develop state-of-the-art imaging systems, instrument tissues, and engineer the immune system. This requires creating groundbreaking datasets to power AI/ML efforts within and across these scientific grand challenges, enabling scientists to better understand human biology and accelerate scientific progress.
Requirements
- 10+ years of experience with large scale high throughput biological data (single cell sequencing, immune receptor profiling, mass spectrometry).
- Demonstrated ability to deliver multiple large biological data products.
- Experience with big data: extraction, transport, loading, databases, standardization, validation, QC, and analysis.
- Experience with processing and orchestration pipelines, such as Argo Workflows, Databricks
- Strong fundamentals in statistical reasoning and machine learning.
- Experience with biological data analysis and QC best practices
- Experience working in a multidisciplinary environment (scientific platforms, engineering, product, AI Research).
Responsibilities
- Contribute the tools required for a robust data ecosystem: build single cell data ingestion pipelines, select data formats, standards, and database schemas, and write validation tools, QC approaches, and analysis pipelines.
- Collaborate with Platform Scientists, ML engineers, AI Researchers, and Data Engineers to iteratively evaluate, refine and grow datasets to improve our biological understanding of inflammation.
- Work closely with Platform Scientists to identify technical variables and devise approaches to harmonize data across generation sites to enable joint analysis.
- Discover and define new data generation opportunities, and manage the delivery of those data products to our scientific teams.
- Lead the creation of groundbreaking datasets that power our AI/ML efforts within and across our scientific grand challenges.
- Define data needs, format standards, analysis approaches and quality metrics and build pipelines to ingest, transform, and validate data products that form the foundation of our experiments.
- Help publish datasets through public resources like CELLxGENE Discover, the CryoET Portal, and the Virtual Cell Platform.
Other
- Excellent written and verbal communication skills.
- Enthusiasm to ramp up on technologies and learn new domains.
- This role is a hybrid position requiring you to be onsite for at least 60% of the working month, approximately 3 days a week, with specific in-office days determined by the team’s manager.
- If you’re interested in a role but your previous experience doesn’t perfectly align with each qualification in the job description, we still encourage you to apply as you may be the perfect fit for this or another role.
