Senior Forward Deployed Engineer (Agentic AI, RAG, Llms)

Staffworx Limited; Greater London; Remote; GBP 90,000 - 130,000; Full time

Job summary

Staffworx Limited is seeking a Senior Forward Deployed Engineer to lead design and delivery of agentic AI solutions for enterprise clients. You will work remotely across the UK, shaping technical direction, scoping engagements and building safe, reliable AI systems with strong engineering craft.

You will collaborate with client stakeholders and internal teams, focusing on prompt design, evaluation loops, and integration with enterprise platforms.

Qualifications

• 6–8 years of software/AI engineering experience.
• Strong hands-on experience with LLMs, embeddings, RAG and vector databases.
• Experience designing or implementing multi-agent systems or tool-calling frameworks.
• Strong prompt engineering skills, including system prompts and structured outputs.
• Experience building evaluation frameworks for LLM or agent behaviour.
• Strong Python skills.

Responsibilities

• Lead technical design within client engagements and set architectural direction across delivery teams.
• Collaborate with client teams remotely and on-site visits to understand workflows and data.
• Turn ambiguous client problems into feasible engineering approaches and fast prototypes.
• Contribute to framing, scoping discussions and technical artefacts for clients.
• Act as the trusted technical voice from workshop to go-live.

Skills

6-8 years

LLM/AI engineering

Embeddings & RAG

Multi-agent systems

Prompt engineering

Evaluation frameworks

Python

Tools

LangGraph

LangSmith

Arize

Braintrust

Semantic Kernel

OpenAI SDK

Anthropic SDK

Job description

Senior Forward Deployed Engineer

LLM, RAG, Agentic AI and Prompt Engineering | Permanent | Remote first, UK

A fast-growing, engineering-led AI consultancy is hiring Lead and Senior Forward Deployed Engineers on a remote-first basis across the UK. You will lead the design and delivery of complex client engagements spanning agentic systems, retrieval architectures and semantic layers, working directly inside enterprise client teams.

Client demand for AI-led transformation is accelerating and our client is expanding its permanent engineering team across agentic systems, retrieval, ontologies and AI-enabled operations. As a Forward Deployed Engineer, you will work closely with the client, in their workshops and inside their systems, turning real operational problems into working AI solutions.

These are senior, hands-on consulting roles that combine deep engineering craft with commercial and product thinking. You will work with senior client stakeholders alongside consulting and delivery colleagues, and lead technical design on your engagements. Prompt design, evaluation and guardrails are central to how you build, so the agents you ship are safe, reliable and measurable once they are live.

You will shape both client outcomes and the firm's long-term AI engineering capability, while staying hands-on in the code.

What you'll do

Embedded client delivery and technical leadership

• Lead technical design within client engagements and set architectural direction across delivery teams
• Work alongside client teams, remotely and on occasional site visits, to understand their workflows, data and constraints first hand
• Turn ambiguous client problems into clear, feasible engineering approaches and fast prototypes for client validation
• Assess client data, platforms, security constraints and operating models
• Contribute to framing, use-case shaping and technical scoping discussions
• Work with client domain experts to surface edge cases and operational realities
• Produce clear, lightweight technical artefacts for client and internal audiences
• Act as the trusted technical voice on the engagement, from first workshop to go-live

Agentic AI, LLM and RAG engineering

• Design and build LLM applications using modern orchestration patterns, prompt frameworks and evaluation loops
• Build multi-agent architectures covering planning, delegation, tool use, memory, safety constraints and monitoring
• Build retrieval and vector-based systems: embeddings, RAG, structured reasoning and semantic workflows
• Connect agents to enterprise platforms through APIs, tools, MCP Servers and connectors
• Apply ontologies or knowledge graphs where they improve reasoning and data alignment

Prompt engineering and evaluation

• Design, test and version system prompts, tool descriptions and agent instructions
• Build reusable prompt libraries and patterns that hold up across clients and use cases
• Create evaluation sets and automated eval loops to measure accuracy, safety and consistency
• Implement guardrails, structured outputs and explainability checks
• Diagnose and fix failure modes such as hallucination, tool misuse and prompt injection

Delivery excellence, AI operations and reliability

• Implement evaluation frameworks and safety checks across models and agents
• Design monitoring, logging, tracing and incident-response patterns for live agents
• Apply governance, risk and compliance principles within client environments
• Support releases, environments and handover into client operations
• Ensure reliability, reproducibility, performance and cost control

Building team capability

• Turn field learnings into reusable agent patterns, templates and accelerators
• Feed client insight back into the wider engineering team and its standards
• Coach peers and share new research, tools and techniques

What you’ll bring

Essential

• 6 to 8 years in software engineering, AI engineering or applied data engineering
• Strong 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, including system prompt design, tool use and structured outputs
• Experience building evaluation frameworks for LLM or agent behaviour
• Strong Python …

Desirable

• Previous forward deployed, solutions engineering or technical leadership experience
• Commercial awareness and product thinking, including scoping and estimating technical work
• Agent frameworks such as LangGraph, CrewAI, AutoGen, Semantic Kernel or the OpenAI and Anthropic agent SDKs
• LLM evaluation and observability tools such as Langfuse, LangSmith, Arize or Braintrust
• Deeper ontology or knowledge graph expertise
• Domain experience in life sciences, pharma or healthcare, FMCG or retail, insurance, or banking and financial services
• Strong engineers from non-AI backgrounds who have moved quickly into agentic AI and can show what they have built are very welcome.