Gen-AI Prompt & Context Engineer; Remote | Outside IR35

We are seeking a Gen-AI Prompt & Context Engineer to design and operate end-to-end LLM workflows, including prompt strategy, retrieval pipelines, multi-agent orchestration, and production observability. The role involves building scalable AI automation using Python, CrewAI multi-agent systems, and n8n workflows while ensuring safety, governance, and performance.

• Design and optimize prompts, templates, and prompt libraries for consistent AI outputs
• Build context pipelines (RAG, embeddings, chunking, hybrid search) and maintain knowledge freshness
• Develop and orchestrate multi-agent workflows using CrewAI and integrate external tools/APIs
• Create automated LLM workflows in n8n with retries, approvals, and monitoring
• Build Python services, evaluation harnesses, and metrics pipelines for LLM performance
• Implement guardrails, RBAC, audit trails, and compliance-aligned AI governance
• Monitor production reliability with tracing, dashboards, alerts, and fallback strategies

• Strong Python engineering and API development experience
• Hands-on experience with prompt engineering, RAG pipelines, and LLM orchestration
• Experience with multi-agent frameworks (e.g., CrewAI) and workflow tools like n8n
• Familiarity with vector databases, embeddings, and hybrid retrieval approaches
• Knowledge of observability, evaluation methods, and AI safety controls
• Strong problem-solving skills and ability to work cross-functionally

• Experience with Open Telemetry, Grafana, or similar monitoring tools
• Exposure to enterprise AI governance, privacy, or regulated environments
• Experience optimizing LLM cost, latency, and accuracy in production systems