Build the core intelligence layer by training and fine-tuning open-source models using proprietary clinical data. Develop rigorous evaluation pipelines and scalable inference infrastructure to power LLM-driven workflows for clinicians.
Develop and scale core backend services and Generative AI workflows using FastAPI and MongoDB/Postgres. Collaborate with the team to prototype MVPs and harden them into secure, reliable production systems on AWS.
Own and build the clinician experience across mobile and web platforms, focusing on robustness and intuitive design. Tackle complex engineering challenges including real-time voice interfaces and offline-first architecture for unreliable connectivity.
