Project Overview A site-centric Clinical Trial Management System (CTMS) that helps research sites efficiently activate and manage studies while ensuring full regulatory compliance. The platform streamlines study start-up, documentation, sponsor communication, and operational workflows in an audit-ready environment.
A core component is an AI-powered protocol engine that converts complex clinical trial documents (100–400+ pages) into structured workflows, extracting key elements such as: * Schedule of Assessments (SoA) * Visit timelines and structures * Inclusion/Exclusion criteria * Investigational product requirements * Regulatory and operational tasks
Key Responsibilities * Design and optimize RAG-based pipelines for medical protocol extraction. * Improve AI performance, traceability, and output validation. * Build and maintain scalable backend systems (FastAPI, PostgreSQL). * Model complex clinical data and ensure auditability/compliance. * Enhance system reliability (logging, monitoring, testing, reproducibility). * Support system validation (CSV) and enforce secure coding practices. * Maintain CI/CD pipelines, Dockerized services, and system scalability.
Required Skills & Experience * 5+ years with Python, FastAPI, SQLAlchemy. * Strong PostgreSQL expertise (design, performance tuning). * Experience with microservices, Docker, and async processing (Celery, Redis, RabbitMQ). * Hands-on experience with RAG systems, LangChain, and vector DBs (pgvector). * Understanding of LLMs, embeddings, and cost/performance trade-offs. * Experience in regulated industries (healthcare, fintech, etc.) is a plus.
Nice to Have * Experience with GxP environments. * Familiarity with Python tooling (Poetry, Ruff, pre-commit). * Experience scaling or re-architecting systems.