AI & Agentic Solutions

Production AI and agents on AWS and Azure

Agentic AI & AI Agents

Build AI agents that act on your systems, with guardrails built in.

Generative AI on Amazon Bedrock

Secure generative AI applications inside your AWS environment.

AI Solutions on Microsoft Foundry

Enterprise AI on Microsoft Foundry and Azure OpenAI.

RAG & Enterprise Knowledge Assistants

Accurate, cited answers from your own documents and data.

AI Platform Foundations & LLMOps

Run AI in production with DevOps discipline.

Data & ML Platform Engineering

Design and build scalable data and ML platforms for analytics and AI workloads

Cloud Architecture & Data Platform Engineering

Design scalable cloud and data platforms that last

Cloud Platform Foundations

Establish secure, scalable cloud landing zones and core platform services

Cloud Strategy & Architecture Reviews

Assess cloud architectures to improve scalability, security, and cost efficiency

Cloud-Native Application Architecture

Design modern, resilient application architectures for cloud-native environments

Hybrid Cloud & Migration

Design, modernise, and operate hybrid and on-prem infrastructure

Hybrid Cloud & Migration

Enterprise-ready hybrid infrastructure, built for scale

DevOps, CI/CD & Infrastructure Automation

Automate infrastructure and delivery pipelines with confidence

DevOps, CI/CD & Infrastructure Automation

Automate delivery. Reduce risk. Scale with confidence.

Cloud Cost Optimisation & FinOps

Control cloud spend with clear visibility and governance

Cloud Cost Optimisation & FinOps

Engineering-led cost optimisation with real, measurable savings

AI Engineer

  • Cardiff - On-site
  • Full time

Job Summary

Cloud DevOps Limited is looking for an AI Engineer to design, build and deploy production-grade AI solutions for our clients, including generative AI applications, retrieval-augmented generation (RAG) systems and AI agents on AWS and Azure. You will work alongside our cloud and DevOps engineers to take AI use cases from prototype to production.

Responsibilities

  • Design and build LLM-powered applications and AI agents using platforms such as Amazon Bedrock and Microsoft Foundry
  • Build RAG pipelines, including document ingestion, chunking, embeddings and vector search
  • Develop evaluation frameworks to measure answer quality, safety and cost before and after each release
  • Deploy and operate AI workloads using infrastructure as code and CI/CD, with monitoring, tracing and cost controls
  • Apply guardrails, access controls and responsible AI practices to every solution
  • Work with clients to understand their use cases and explain technical decisions clearly
  • Document solutions and share knowledge with the wider team

Requirements

  • Strong Python skills and a solid grounding in software engineering practice
  • Experience building applications with large language models and orchestration frameworks such as LangChain, LangGraph or LlamaIndex
  • Hands-on experience with AWS and/or Azure
  • Understanding of machine learning fundamentals, embeddings and vector databases
  • Experience with Git, CI/CD, Docker and infrastructure as code
  • Clear communication and a practical, problem-solving approach
  • A degree in computer science, data science or a related field, or equivalent practical experience

Nice-to-Have Skills

  • AWS Certified Machine Learning Engineer – Associate or an equivalent Azure certification
  • Experience with MLOps, model evaluation and observability tooling
  • Experience with Terraform and Kubernetes
Apply Now