Senior Forward Deployed Engineer (LLM, RAG & Agentic AI)

Senior-forward deployed engineer at a fast-growing AI consultancy. You will lead embedded client engagements, shaping technical design and delivery of agentic AI, RAG, and prompt engineering solutions. You work closely with client teams to translate operational problems into verifiable, live AI capabilities while advancing the firm’s engineering capabilities. This role blends hands-on coding with strategic, client-facing impact in a remote-first UK setting.

• remote-first
• permanent role
• bonus
• full benefits

• Lead technical design within client engagements and set architectural direction across delivery teams
• Collaborate with client teams remotely and on-site to understand workflows and data
• Translate ambiguous problems into feasible engineering approaches and prototypes
• Assess client data, platforms, security, and operating models
• Frame use-cases and contribute to technical scoping discussions
• Surface edge cases with domain experts and surface operational realities
• Produce clear technical artefacts for clients and internal audiences
• Act as trusted technical voice from workshop to go-live
• Design and build LLM applications with modern orchestration patterns and evaluation loops
• Build multi-agent architectures with planning, delegation, memory, safety, and monitoring
• Connect agents to enterprise platforms via APIs, tools, MCP servers, and connectors
• Apply ontologies or knowledge graphs for reasoning and data alignment
• Design, test, and version system prompts, tool descriptions, and agent instructions
• Create reusable prompt libraries and evaluation sets with automated loops
• Implement guardrails, structured outputs, and explainability checks
• Diagnose and fix failure modes such as hallucination and prompt injection
• Design monitoring, logging, tracing, and incident-response for live agents
• Apply governance, risk, and compliance in client environments
• Support releases, environments, and handover to client operations
• Turn field learnings into reusable patterns and accelerators
• Coach peers and share new tools and techniques

• 6–8 years in software/AI engineering or applied data engineering
• Hands-on experience with LLMs, embeddings, RAG, retrieval stacks, and vector databases
• Experience designing or implementing multi-agent systems or tool-calling frameworks
• Strong prompt engineering skills (system prompts, tool use, structured outputs)
• Experience building evaluation frameworks for LLM or agent behavior
• Strong Python with production-grade systems experience
• Experience with at least one major cloud AI ecosystem (Azure OpenAI, Vertex AI, AWS, or Anthropic)
• Familiarity with semantic modeling, ontologies, or knowledge graphs
• Proven ability to rapidly prototype solutions for client validation
• Experience working directly with clients in consulting or professional services

• Excellent client-facing communication
• Commercial awareness and product thinking
• Collaborative and results-driven
• LLMs, embeddings, RAG, retrieval stacks, vector databases
• Multi-agent systems, tool-calling frameworks
• Prompt design and evaluation