Prompt Engineer - LLM/Copilot

Summer-Browning Associates Ltd; City Of London; Hybrid; GBP 45,000 - 65,000; Part time

Job summary

A consultancy firm is seeking a Prompt Engineer (LLM/Copilot) for a hybrid role located in London. The role involves designing AI prompts, analyzing model outputs, and collaborating with teams to enhance user value. Candidates should have experience in AI-driven solutions and a commitment to public service. The contract duration is initially for 4 months, requiring a successful BPSS check.

Qualifications

• Experience in designing and refining prompts for AI.
• Proven track record in delivering enterprise-scale AI solutions.
• Ability to present findings to stakeholders.

Responsibilities

• Developing and maintaining prompt libraries and templates.
• Implementing prompt evaluation frameworks and metrics.
• Staying updated with advancements in LLMs and prompt engineering.

Skills

Prompt engineering

AI-driven solutions

Collaborating with cross-functional teams

Analyzing model outputs

Job description

Summer-Browning Associates are currently supporting our Central Government client who are seeking a Prompt Engineer (LLM/Copilot) on an initial 4 month contract

Service Location: London (hybrid)

We are seeking individuals with a strong commitment to public service and a proven track record in delivering enterprise-scale, AI-driven solutions.

You will have experience in:

• Designing, developing, and refining prompts for copilots and AI agents to maximise accuracy, safety, and user value.
• Analysing model outputs and conversational logs to identify improvement opportunities and failure points.
• Developing and maintaining prompt libraries, templates, and best practice documentation.
• Collaborating with cross-functional teams to align prompt engineering with business goals and user needs.
• Implementing prompt evaluation frameworks and metrics to assess performance and reliability.
• Staying up to date with the latest advancements in LLMs, prompt engineering, and agentic AI.
• Presenting findings and recommendations to technical and non-technical stakeholders.

Desirable (but not essential):

• Experience with frameworks for autonomous agents (e.g., AutoGPT, CrewAI, LangGraph, ReAct, BabyAGI).
• Background in human-AI interaction, conversational UX, or simulation environments.
• Knowledge of vector databases or retrieval-augmented generation (RAG).
• Understanding of the ethical, social, and safety considerations of autonomous AI systems.

NB: Successful applicant will be brought on board with a completed BPSS check and be eligible for SC level vetting.

To apply, please submit latest CV for review