• Development and deployment of LLM-powered features, including summarization tools and clinician-facing conversational agents • Build backend services in Python that integrate ML/LLM models with Fullscript’s platform • Implement prompt engineering techniques to optimise model outputs • Implement AI feature quality testing, CI/CD pipelines, and version control for all model-related workflows • Collaborate with medical and product teams to deliver AI features for practitioners and patients • Work cross-functionally with engineering, analytics, and medical SMEs to refine requirements and ensure data solutions support clinical contexts • Stay current with the latest LLM research and emerging AI technologies

• Support customers and join the passionate team of high-impact problem solvers • Work cross-functionally to design, plan, implement, and guide enterprise AI/ML strategies • Be a technical advisor who will help lead and direct the execution of advanced machine learning solutions • Oversee all aspects of the ML lifecycle, including data collection, cleaning, pre-processing, model training, and production deployment • Assist customers in developing new business opportunities until a suitable long-term project for growth is identified.

• Design and build Machine Learning platform components that support agentic systems, including retrieval pipelines, indexing strategies, and model integration layers. • Introduce and operationalize RAG use cases, from data sourcing and embedding generation to runtime retrieval patterns. • Develop generalized evaluation frameworks for LLM- and agent-based features, including offline metrics, golden datasets, and continuous monitoring. • Implement abstractions, tooling, and reusable patterns that enable other teams to build ML- and LLM-powered experiences efficiently. • Partner with backend engineers to productionize ML features with strong reliability, observability, and performance characteristics. • Prototype applied ML solutions to validate feasibility before investing in full builds. • Ensure secure, robust handling of data used in ML workflows and retrieval operations. • Collaborate with product, design, and engineering to align ML system design with user experience and product goals. • Contribute to iterative improvements of the Nova agent framework, including workflows built with Mastra and TypeScript.

• Design, maintain, automate, and optimize ML training pipelines and realtime model serving infrastructure • Improve ML observability, model evaluations, model monitoring, and debugging tools • Collaborate closely with ML scientists and engineering teams • Develop new ML solutions to extract information from studio artifacts • Stay updated with ML infrastructure advancements and new technologies