We’re building an agentic platform at the intersection of medicine and law, transforming complex, high-stakes casework into structured, actionable context. Our system handles patient records, legal workflows, and sensitive decisions, so reliability, clarity, and thoughtful engineering matter deeply.
As a software engineer, you’ll work across the full stack: agent architectures, evals, the data and context that feed them, and the surfaces to interact with the platform and its harness.
In a given week, that might mean
• building and shipping a new workflow that takes over a step of the case process, driven by something a physician or our ops team flagged
• designing the eval framework that decides whether an agent’s output is reliable enough to ship, while piping the feedback into our synthesized knowledge base
• improving how the platform ingests, indexes, and assembles the right case context for an agent to work from
• adding new tooling to the interfaces users interact with day to day, bringing more of the platform’s context and agent capabilities into their workflow
• iterating quickly on a feature with direct input from users, refining the agents based on real-world usage and feedback
• setting the patterns and tooling for AI-native development that the rest of the team builds on