Senior/ Staff Software Engineer, Imaging

The role

You will define and expand data and ML infrastructure across the full data lifecycle. You will build platform features for in vitro screening modalities and ML-derived phenotypes to process terabytes of biological data per day.

What you will do

• Partner with lab and ML scientists to design, develop, and scale platform capabilities.
• Build and evolve tools and interactive interfaces for data exploration, quality assessment, and visualization.
• Own complex, end-to-end projects and make architectural trade-offs.
• Scale and harden complex ML workflows to process terabytes of data per day.
• Set and uphold practices for data integrity, lineage tracking, reproducibility, and observability.
• Write technical specifications and documentation.
• Translate complex experimental needs into technical plans and software.
• Mentor other engineers.

Required qualifications

• 6+ years of professional experience building and operating production-grade software and high-throughput data pipelines, primarily in Python.
• Hands-on experience with a Python-first ML stack (PyTorch/Lightning).
• Hands-on experience with distributed compute (Ray, Dask, Kubernetes, etc.).
• Hands-on experience with workflow orchestration (Argo, Airflow, redun, etc.).
• Experience deploying on cloud infrastructure at multi-terabyte scale.
• Track record of owning complex systems from architecture through production operation.

Nice to have

• Designed, built, and maintained scientific computing pipelines, visualizations, and QC processes for large-scale biological datasets.

Benefits

• 401(k) plan with employer matching
• Medical, dental, and vision coverage
• Mental health and well-being support
• Open, flexible vacation policy
• Paid parental leave of at least 16 weeks for birth parents and 10 weeks for new parents
• Quarterly budget for books and online courses
• New hire stipend for home office setup
• Monthly cell phone and internet stipend
• Free onsite baristas and daily lunch for onsite or hybrid employees
• Free commuter bus network

About the company

insitro is a physical AI company and drug discovery and development company using machine learning and data at scale to decode biology. The company uses a Virtual Human platform and TherML platform to identify genetic intervention points and translate them into therapeutics.