LLM EngineermidCardiff, Wales, UKremotefulltimeTechnology, Information and InternetPythonLLMsRAGembeddingsAPIsDockerKubernetesagentic workflowsposted 20 Jul
We're working with a fast-growing technology business investing heavily in AI-driven product development and intelligent automation. They are seeking an experienced AI Engineer to help build scalable, production-grade AI systems that deliver significant commercial impact across their platform. This is a hands-on engineering role focused on designing, building, and deploying AI capabilities into live products used by customers globally.
The Role
* Build and deploy production AI applications using large language models (LLMs)
* Design agentic workflows and multi-step AI pipelines
* Develop scalable backend APIs and cloud-native services
* Create Retrieval Augmented Generation (RAG) pipelines, embeddings, and AI retrieval systems
* Improve AI reliability through testing, evaluation, and guardrails
* Contribute to architecture decisions and AI best practices
What You'll Need
* Strong Python backend engineering experience
* Experience building and deploying LLM-based applications
* Good understanding of APIs, distributed systems, and cloud platforms
* Hands-on experience with RAG, embeddings, and AI orchestration
* Experience with Docker/Kubernetes and modern engineering practices
* Comfort operating in a fast-moving product environment
What's On Offer
* Opportunity to work on genuinely cutting-edge AI products
* High-impact engineering role with real ownership
* Modern tech stack and AI-first environment
* Fully remote flexibility
Apply via Haystack today!
More LLM Engineer roles like this, weekly
Roles like this expire in about a week. Get new LLM Engineer openings across the UK in your inbox — free, unsubscribe any time.