AI Engineer

h3Job Description /h3pAt CluePoints, we’re redefining how clinical trials are run. As the premier provider of Risk-Based Quality Management (RBQM) and Data Quality Oversight software, we harness advanced statistics, artificial intelligence, and machine learning to ensure the quality, accuracy, and integrity of clinical trial data, helping life sciences organisations bring safer, more effective treatments to patients faster. /ph3Job Description /h3pAt CluePoints, we’re redefining how clinical trials are run. As the premier provider of Risk-Based Quality Management (RBQM) and Data Quality Oversight software, we harness advanced statistics, artificial intelligence, and machine learning to ensure the quality, accuracy, and integrity of clinical trial data, helping life sciences organisations bring safer, more effective treatments to patients faster. /ppWe’re an ambitious, fast-growing technology scale-up with a dynamic and diverse international team. Collaboration, flexibility, and continuous learning are part of our DNA, and we are guided by our values of Care, Passion, and Smart Disruption. /ph3The Role /h3pThe AI Engineer will build the AI capabilities that sit on top of CluePoints’ new data layer: the platform that harmonizes data across clinical studies and applications and makes it available to CluePoints’ consumer applications. You will design, evaluate and ship AI solutions, such as metadata-driven variable harmonization and retrieval and knowledge-graph services, that are auditable, traceable and fit for a regulated clinical-trial environment. /ppCluePoints has committed to building this data layer, so the role is an opportunity to shape the AI approach from the start. Success looks like AI components that measurably accelerate harmonization and whose outputs can be explained and defended in front of an auditor. /ph3Job Requirements /h3ulliDemonstrated experience building and shipping AI solutions into production, not only prototypes. /liliHands-on experience with RAG, including retrieval design, grounding and evaluation of results. /liliWorking knowledge of knowledge graphs, including when they are and are not the right tool. /liliStrong Python skills and solid software-engineering fundamentals (testing, code review, API design). /liliExperience evaluating AI outputs systematically, using test sets, accuracy measures and regression checks. /liliUnderstanding of regulatory compliance, auditability and traceability in platform and system design. /liliComfort evolving quickly and experimenting with different technology capabilities, choosing solutions on evidence. /liliAbility to work with data from multiple sources whose structures and variables differ. /liliAbility to explain complex technical concepts clearly to technical and non-technical stakeholders. /li /ulh3Nice To Haves /h3ulliExperience in clinical trials, life sciences or another regulated environment. Strong candidates from other sectors, such as fintech, will be considered. /liliFamiliarity with Databricks and/or Snowflake and with Microsoft Azure. /liliFamiliarity with spec-driven development frameworks such as BMAD, Superpowers or Spec Kit. /liliExposure to clinical data standards (for example CDISC) or to metadata from electronic data-capture systems. /liliExperience building structured AI workflows, such as prompt pipelines, agent orchestration or automated review. /li /ulh3Job Responsibilities /h3h3AI Solution Design Delivery /h3ulliDesign, build and ship AI solutions that support the data layer, including approaches that use metadata from data-capture solutions to help harmonize differing study variables. /liliEvaluate and experiment with AI and retrieval options (LLMs, RAG, knowledge graphs) and recommend the approach best suited to each problem rather than defaulting to the newest tool. /liliPrototype quickly against realistic study data, then take successful prototypes through to production-quality services. /li /ulh3Retrieval Knowledge Graphs /h3ulliDesign and implement RAG pipelines over study metadata, data dictionaries and variable definitions. /liliApply knowledge-graph approaches to model relationships between studies, variables and concepts where they add value over conventional structures. /liliExpose AI and retrieval capabilities through well-defined interfaces that CluePoints’ consumer applications can use. /li /ulh3Evaluation, Auditability Compliance /h3ulliDefine evaluation methods and quality thresholds for AI outputs, such as proposed variable mappings, and measure them against reviewed examples. /liliMake AI-supported outputs traceable and auditable, with versioned prompts, models and configurations and a clear record of what was generated and what a person approved. /liliBuild proportionate human-review controls into AI-assisted harmonization workflows. /liliWork with the architect to ensure AI components meet regulatory compliance expectations within the platform design. /li /ulh3Collaboration Engineering Practi