Generative AI Engineer — Remote-First, AWS Bedrock

Amber Labs; Greater London; Hybrid; GBP 80,000 - 110,000; Full time

Benefits offered by this job

25 days annual leave

Private medical insurance

Remote-first working

Training budget

Perkbox membership

EV scheme

Pension contributions

Referral scheme

Job summary

Amber Labs in the UK is seeking an experienced AI Engineer to design, build and deploy AI-powered solutions within secure government‑facing environments. You will work in multidisciplinary teams using AWS Bedrock and Python to deliver scalable capabilities across service management and automation.

You will collaborate with software, cloud, architecture and product teams in an agile setting, driving prompt engineering, RAG workflows and production‑ready AI services while ensuring resilience and

Qualifications

• Experience building AI-powered solutions in secure or regulated environments.
• Proficient in Python and cloud-based AI services.
• Experience with agile development and cross-functional teams.

Responsibilities

• Design and build AI-powered workflows using large language models through AWS Bedrock.
• Develop prompt engineering approaches to support production AI use cases.
• Implement Retrieval-Augmented Generation (RAG) patterns to improve response quality and knowledge retrieval.
• Build structured output generation and intelligent automation capabilities.
• Integrate AI capabilities with enterprise service management platforms such as Jira and Confluence.

Skills

LLM knowledge

Prompt engineering

Python development

AWS cloud services

DevOps / CI/CD

Stakeholder communication

Tools

AWS Bedrock

Jira

Confluence

Job description

Amber Labs in the UK is seeking an experienced AI Engineer to design, build and deploy AI-powered solutions within secure government‑facing environments. You will work in multidisciplinary teams using AWS Bedrock and Python to deliver scalable capabilities across service management and automation.

You will collaborate with software, cloud, architecture and product teams in an agile setting, driving prompt engineering, RAG workflows and production‑ready AI services while ensuring resilience and