Senior AI Engineer – Synthetic Agents & Behavioural ModellingLondon | Office-first (4 days/week)A well-funded, science-led AI company is hiring a Senior AI Engineer to join its core Science team as it scales a platform that builds synthetic populations capable of predicting real-world human behaviour.The company operates at the intersection of behavioural data, statistical modelling and generative AI, building simulation systems that model collective human decision-making. Its technology is already deployed in enterprise environments where insight quality, speed and robustness directly impact strategic outcomes.This is not a generic LLM engineering role. It sits at the intersection of research, behavioural modelling and production AI systems — designing the cognitive architectures that power realistic synthetic agents, and working closely with engineering to scale them reliably.The RoleAs a Senior AI Engineer, you will sit within the Science team, working on the research, design and implementation of AI agent systems that simulate human behaviour at scale.You will:Design and run structured experiments to evaluate and improve synthetic agent behaviourDevelop and iterate on agent cognitive architectures (memory, reasoning, personality and context systems)Build sophisticated prompting and behavioural frameworks that enable realistic decision-makingValidate model outputs against real-world data using statistical and experimental methodsWork closely with backend engineering to scale agent systems into robust production environmentsBalance research exploration with practical delivery in an evolving product environmentThis role is ideal for someone who enjoys both thinking deeply about models and behaviour and building real systems that operate reliably in enterprise settings.Example ProjectsDesigning memory and context systems that allow agents to maintain coherent beliefs and behaviour over timeRunning behavioural experiments to test whether simulated populations align with observed real-world outcomesComparing prompting strategies, model variants or fine-tuning approaches to improve behavioural realismBuilding multi-agent systems where agents reason, debate, retrieve evidence and update beliefsDiagnosing behavioural drift and improving model robustness through structured experimentationWhat You’ll BringResearch & ModellingEvidence of running experiments to validate model behaviour and performanceExperience iterating quickly on model architectures based on empirical resultsUnderstanding of statistical validation and data quality assessmentExposure to research-driven product development or academic AI researchLLM & Agent DevelopmentHands-on experience building applications on top of large language modelsExperience with advanced prompting, RAG systems and agentic workflowsExposure to multi-agent systems, simulation frameworks or agent-based modellingFamiliarity with frameworks such as PyTorch, Hugging Face, LangChain or similarBackend EngineeringStrong Python skills with backend frameworks (FastAPI, Django, Flask or similar)Understanding of scalable architectures and distributed systemsComfort taking systems from prototype through to production deploymentWho You AreStrong ownership mentality — you see ideas through from concept to deploymentIntellectually rigorous — you question assumptions and adjust direction based on evidenceComfortable working in ambiguity and fast-evolving environmentsCollaborative and direct — able to debate ideas constructivelyGenuinely motivated by understanding how AI systems behave, not just wiring them togetherWhat’s On OfferCompetitive salary with meaningful equityOffice-first culture in central London (4 days/week, non-negotiable)Direct collaboration with senior scientific and technical leadershipThe opportunity to work on AI systems that influence real-world, high-stakes decisionsLong-term growth within a company scaling both its applied research capability and product footprint