Prometheus Biosciences

Our team operates on 1-2 week sprints that begin with a planning meeting that ends in defined tasks with specific owners, acceptance criteria, and estimated time to completion.

Halfway through the sprint, we refine our backlog.

Sprints end with a Friday afternoon retro, where we share what went well, what can be improved, and action items for the team.

Code lives on GitHub. We do code reviews before PRs are merged. We'd like to set up automated CI/CD where appropriate.

We are still determining project management tools for agile. Currently the debate is Notion vs GitHub.

We currently do standup twice a week, but are thinking of moving to a Tuesday AM planning meeting with daily asynchronous checkins via Slack.

We're ingesting, standardizing, and version-controlling multimodal biomedical data, including gene sequence, protein expression, histopathology (images of tissue slices), tabular electronic medical record data, and more.

Labels defining a clinical phenotype (e.g. did the patient respond well to therapy?) change over time and vary depending on the definition applied, so we must develop a lightweight and programmatic way of defining labels for supervised learning.

We need to performantly query and visualize these data, and serve applications to non-techncial R&D scientists so they can do the same and become more proficient with modern data science tools.

We also will build a suite of ML/DL tools for power users .

As part of our commitment to an inclusive workplace, we are happy to offer prospective engineers the chance to connect with our engineering employees who come from underrepresented backgrounds. It’s a way to get a better sense of our team and what it might be like to work with us.

If you’re interested in connecting with our team, be sure to bring this up during one of our introductory calls!