AI Engineer: LLM Apps, RAG Pipelines, Cloud Native

Halian Technology Limited; Reading; Hybrid; GBP 80,000 - 110,000; Full time

Benefits offered by this job

Private medical cover

Job summary

Halian Technology Limited is seeking an experienced AI Engineer to design and build LLM-based applications, including RAG pipelines and copilots, for a healthtech-focused platform. You will develop scalable backend services in Python and Java, integrating AI capabilities into cloud-native SaaS and owning end-to-end delivery from prototyping to production.

Hybrid role based in Reading with a real impact on AI strategy, architecture, and delivery.

Qualifications

• We are looking for 5+ years of software engineering experience with strong Python/Java.
• Practical experience with LLMs, prompt engineering, embeddings and RAG.
• Experience deploying in cloud environments (Azure preferred; AWS/GCP also ok).
• Strong knowledge of APIs, microservices and distributed systems.
• Docker, Kubernetes and CI/CD pipelines familiarity required.
• SQL and NoSQL data stores and large datasets experience welcomed.
• LangChain and LlamaIndex experience is a bonus.
• A relevant degree is beneficial but practical engineering experience is primary.

Responsibilities

• Design and implement LLM-based applications such as RAG pipelines, agents and copilots.
• Build scalable backend services using Python and Java.
• Integrate AI capabilities into cloud-native SaaS platforms.
• Own full lifecycle from experimentation to production deployment.
• Optimize model performance, cost and latency in real-world environments.
• Collaborate with engineering, product and data teams on AI use cases.

Skills

Python

Java

LLMs

Prompt engineering

Fine-tuning

Embeddings

Vector databases

RAG

APIs

Microservices

Distributed systems

Docker

Kubernetes

CI/CD

SQL

NoSQL

LangChain

LlamaIndex

Azure

AWS

GCP

Education

Relevant degree (beneficial)

Tools

Azure

AWS

GCP

Job description

Halian Technology Limited is seeking an experienced AI Engineer to design and build LLM-based applications, including RAG pipelines and copilots, for a healthtech-focused platform. You will develop scalable backend services in Python and Java, integrating AI capabilities into cloud-native SaaS and owning end-to-end delivery from prototyping to production.

Hybrid role based in Reading with a real impact on AI strategy, architecture, and delivery.