About the job
As a Staff Software Engineer on our Imaging Software team, you will define and expand our computer vision and ML infrastructure across the full imaging data lifecycle — from on-microscope acquisition to high-throughput ML pipelines. You'll build the platform features that make novel imaging modalities and ML-derived phenotypes integral to our discovery workflows, partnering daily with lab scientists, ML scientists, and our microscopy team to turn research prototypes into validated screening workflows that run reliably at laboratory automation scale. This is a chance to set the technical direction for how imaging, automation, and machine learning converge in drug discovery.
Responsibilities
• Partner with lab and ML scientists to design, develop, and scale the platform capabilities needed to run and interpret ML-powered high-content imaging screens
• Build and evolve robust tools and interactive interfaces for data exploration, quality assessment, and visualization so scientists can iterate quickly on experimental data
• Own complex, end-to-end projects, making thoughtful architectural trade-offs, and delivering incrementally with long-term maintainability in mind
• Scale and harden complex image processing and ML workflows, taking them from research prototypes to systems that reliably process millions of images per day
• Set and uphold best-in-class practices for data integrity, lineage tracking, reproducibility, and observability across the entire imaging data lifecycle
• Write clear, exemplary technical specifications and documentation that others build on
• Work closely with lab scientists, ML scientists, and microscopy teams to translate complex experimental needs into clear, actionable technical plans and shipped software
• Raise the technical bar across the team by sharing knowledge and mentoring other engineers
Qualifications
Minimum
• 8+ years of professional experience building and operating production-grade software and high-throughput data pipelines, primarily in Python
• Designed, built, and deployed scientific computing pipelines, visualizations, and QC processes for large-scale imaging or similarly high-dimensional datasets
• Hands-on experience with a Python-first ML stack, distributed compute (e.g., PyTorch/Lightning, Ray, Kubernetes), and workflow orchestration (e.g., Argo, Airflow, or redun)
• A track record of owning complex systems from architecture through production operation
Preferred
No preferred qualifications listed.