Enterprise AI Engineer: LLMs, RAG & AI Agents

Ascendion; Chester; On-site; GBP 90,000 - 130,000; Full time

Job summary

Ascendion is seeking an experienced AI Engineer to design, build, and deploy enterprise-grade AI applications. The role focuses on LLMs, RAG, AI agents, and cloud-based AI services, with a preference for experience in Banking or Financial Services.

You will design and develop AI-powered applications, create prompt strategies, and expose capabilities via REST APIs. Collaboration with Data Engineering and Cloud teams is essential.

Qualifications

• Experience building enterprise AI applications using LLMs and RAG.
• Experience with AI agents, prompt engineering, and API development.
• Knowledge of scalable cloud AI services and secure AI practices.

Responsibilities

• Design and develop AI-powered applications using Large Language Models.
• Develop AI agents and workflow automation solutions.
• Create prompt engineering strategies and evaluation frameworks.
• Develop REST APIs and microservices to expose AI capabilities.
• Work closely with Data Engineering and Cloud teams.
• Implement secure, responsible AI practices.
• Monitor model performance and optimise latency and cost.
• Participate in architecture discussions and code reviews.

Skills

Lang Chain

Lang Graph

Llama Index

Semantic Kernel

Crew AI

RAG

Vector Databases

Embeddings

Prompt Engineering

AI Agents

Function Calling

MCP

Fine Tuning

REST

FastAPI

Flask

Job description

Ascendion is seeking an experienced AI Engineer to design, build, and deploy enterprise-grade AI applications. The role focuses on LLMs, RAG, AI agents, and cloud-based AI services, with a preference for experience in Banking or Financial Services.

You will design and develop AI-powered applications, create prompt strategies, and expose capabilities via REST APIs. Collaboration with Data Engineering and Cloud teams is essential.