8 of 8 Contract Human-in-the-Loop Jobs in London

concept. Responsibilities: Agentic AI: Design and build multi-step agent workflows using LangGraph, including tool calling, state management, routing and human-in-the-loop controls. GenAI & LLMs: Develop LLM-powered applications using Python, prompt engineering, structured outputs and context management. RAG & Knowledge Retrieval: Build ...

concept. Responsibilities: Agentic AI: Design and build multi-step agent workflows using LangGraph, including tool calling, state management, routing and human-in-the-loop controls. GenAI & LLMs: Develop LLM-powered applications using Python, prompt engineering, structured outputs and context management. RAG & Knowledge Retrieval: Build ...

implementing Agentic AI workflows Experience with LangGraph Strong understanding of LLM workflow design, including state, routing, tools, structured outputs and human-in-the-loop patterns Practical experience designing and implementing RAG architectures Experience with document ingestion, chunking, embeddings and vector/semantic search Experience with prompt ...

LLMs, RAG and agentic AI. Conduct technical feasibility assessments and build-versus-buy analysis. Define AI integration patterns, security controls and human-in-the-loop requirements. Assess AI risks, including hallucinations, prompt injection and sensitive-data exposure. Develop architectural recommendations and a phased implementation roadmap. Essential ...

decision-making Build in identity, data protection, resilience, observability, and cost from day one Design evaluation, fallback, escalation, and human-in-the-loop mechanisms Produce architecture decisions, patterns, and reusable reference designs Review implementations and guide engineering teams through major technical decisions What ...

Controls: Demonstrable expertise configuring and implementing Google Cloud VPC Service Controls. Key requirement. AI Security & Guardrails: Experience implementing AI security controls, human-in-the-loop approval processes, prompt protection and PII masking. Identity & Access Management: Strong knowledge of IAM, identity federation, Workload Identity Federation ...

complex enterprise environments. AI Guardrails & Perimeter Defence Hands-on experience designing deterministic AI safety controls and secure AI architectures. Knowledge of human-in-the-loop approval mechanisms, VPC Service Controls, Workload Identity Federation (WIF), and Microsoft Entra ID. Experience establishing privacy, data protection, and Personally Identifiable ...

Evaluation & Feedback Loops: Establish continuous monitoring mechanisms and evaluation frameworks beyond baseline accuracy (including precision, recall, calibration, and robustness metrics). Human-in-the-Loop & Trust Design: Design confidence-based interfaces, exception handling patterns, and transparent AI explainability mechanisms to build operational trust. Data Governance & Ethical … in Visual Design, Typography, Complex Workflow Prototyping, and Enterprise Design Systems. AI Product Management Expertise in scoping AI MVPs, Human-in-the-Loop UX, confidence indicators, and model transparency. Evaluation & Metrics Strategy Proficiency in designing evaluation pipelines beyond accuracy (precision, recall, calibration, robustness ...