AI Engineer – Production LLM Systems

Are you passionate about building real, production‐grade AI systems—not just prototypes or research models?

We’re partnering with a fast‐growing, well‐funded AI‐native consultancy that delivers enterprise‐scale AI solutions to major organisations across Financial Services, Energy, Healthcare, Retail, and Manufacturing.

Working alongside global partners such as Anthropic, Databricks, AWS, OpenAI, and Microsoft, the team focuses on designing and deploying advanced AI systems that solve complex real‐world problems with speed, clarity, and measurable impact.

As part of their expansion, we are looking for experienced AI Engineers who can build robust, scalable applications powered by large language models.

The Role

As an AI Engineer, you will design, build, and deploy production‐grade LLM‐powered systems.

This role sits at the intersection of software engineering, AI implementation, and agentic orchestration.

You will work on:

• Multi‐agent architectures
• Intelligent tool and API integrations
• RAG pipelines and vector‐based retrieval
• Evaluation frameworks and AI observability
• Production workflows that ensure reliability, consistency, and scale

You’ll play a critical role in crafting the orchestration layer that makes LLM systems trustworthy—handling failure modes, optimising agent collaboration, and improving robustness across diverse use cases.

Key Responsibilities

• Build production AI systems using LLMs, RAG pipelines, vector databases, and agentic frameworks
• Design evaluation and observability frameworks to measure performance, accuracy, and reliability
• Develop clean, scalable applications with proper error handling, APIs, and data pipelines
• Implement and maintain retrieval systems (vector/graph databases, ingestion pipelines, chunking strategies, advanced retrieval methods such as HyDE)
• Integrate feedback loops to improve system behaviour over time
• Craft effective prompts and optimise latency, cost, and output quality across multiple model providers
• Collaborate closely with engineering, product, and data teams to build enterprise‐ready AI solutions

Required Skills & Experience

• Hands‐on experience building applications using LLM APIs
• Deep understanding of model capabilities, limitations, and failure modes
• Practical experience with RAG, vector databases, knowledge graphs, and prompt engineering
• Experience building multi‐step LLM workflows and agentic systems (e.g. LangChain, LangGraph, Claude Agents SDK, Strands, or custom frameworks)
• Strong proficiency in Python (or similar language) and developing production APIs/services
• Cloud experience with AWS, GCP or Azure
• Solid understanding of distributed systems, CI/CD, testing frameworks, and deployment pipelines
• Experience designing or operating cloud‐native, production‐grade infrastructure
• Strong data manipulation skills (Pandas, SQL)
• Ability to optimise non‐deterministic systems through experimentation while balancing latency, cost, and quality

Nice to Have

• Experience with AI‐assisted coding (Claude Code, GitHub Copilot, etc.)
• Experience fine‐tuning LLMs or deciding when to use fine‐tuning vs RAG/prompting
• Exposure to streaming, multimodal models, or search technologies (Elasticsearch, etc.)
• Familiarity with observability tools (LangSmith, Weights & Biases)
• Experience in regulated or industry‐specific environments (finance, energy, healthcare, legal, retail)
• Experience developing tool‐calling agents, hand‐offs, and guardrails

What’s on Offer

• A fast‐growing organisation with significant opportunities for career progression
• Highly competitive salary + bonus
• A collaborative, engineering‐driven culture where you’ll make an impact from day one
• Financially strong, well‐backed business with global expansion plans
• Choose your own gear (MacBooks, PCs, accessories)
• Dedicated learning & development budget