Artificial Intelligence Engineer

Opportunitywe're
London, UK
about 2 months ago

Role details

Contract type
Permanent contract
Employment type
Full-time (> 32 hours)
Experience level
Expert
Working hours
Regular working hours
Languages
English
Job source

Tech stack

Artificial Intelligence Software Applications Microsoft Azure Continuous Delivery Identity and Access Management Software Product Management Software Engineering Systems Integration TypeScript AI Infrastructure Large Language Models Prompt Engineering
+4 more
Generative AI Build Management Deployment Automation Virtual Agents

Job description

About the OpportunityWe’re partnering with a forward-thinking eCommerce agency that is investing heavily in AI and automation to transform how businesses operate and scale. As demand for AI-powered solutions continues to grow, they’re looking to appoint a Senior AI Engineer to help design, build and deploy intelligent systems that deliver measurable commercial impact for clients.This is an opportunity to work at the cutting edge of Agentic AI, Large Language Models (LLMs), workflow automation and Retrieval-Augmented Generation (RAG), taking solutions from initial concept through to secure, production-ready deployment. You’ll join a collaborative environment where engineering excellence, innovation and ownership are highly valued, with the chance to influence both technical direction and delivery approaches across a variety of client projects. The RoleAs a Senior AI Engineer, you’ll play a key role in designing and delivering AI-powered applications and autonomous workflows for a diverse client base.Working closely with clients, stakeholders and delivery teams, you’ll be responsible for turning business requirements into scalable technical solutions, while ensuring security, reliability and performance remain at the forefront of everything you build. Key responsibilities will include:Designing and developing production-grade AI applications and agentic workflowsBuilding and maintaining Retrieval-Augmented Generation (RAG) systems and knowledge retrieval architecturesCreating custom MCP servers, integrations, tools, plugins and reusable agent capabilitiesEngineering prompts, context management strategies and workflows that enable AI agents to operate effectively and safelyDeveloping evaluation frameworks to assess and improve LLM performance and output qualityImplementing CI/CD pipelines and deployment automation to support scalable deliveryEnsuring appropriate security, access controls and GDPR compliance when working with client systems and dataCollaborating directly with clients to understand requirements, provide technical guidance and deliver successful outcomesTaking ownership of projects from prototype through to production deployment and ongoing optimisation

Requirements

About YouWe’re looking for someone who has already delivered real-world AI solutions and can confidently bridge the gap between experimentation and production.You’ll bring a combination of strong engineering fundamentals, practical AI experience and the ability to work autonomously in a client-facing environment. Essential ExperienceProven experience using AI-assisted development tools and agent platforms to build and ship real-world applicationsStrong software engineering skills using TypeScript and/or PythonExperience building and deploying RAG applicationsHands-on experience developing custom agent tools, plugins, skills and MCP serversStrong understanding of prompt engineering, context engineering and agent orchestrationExperience designing systems that interact securely with live business data and user permissionsKnowledge of security best practices, access management and GDPR considerationsExperience implementing CI/CD pipelines and automation workflowsDemonstrable ability to take ideas from proof-of-concept through to production-grade deliveryStrong communication and stakeholder management skillsAbility to work proactively, make sound engineering decisions and take ownership of deliveryBusiness-level English, with the ability to gather requirements directly from clients and communicate clearly both verbally and in writing Desirable ExperienceMicrosoft Azure, particularly Azure AI infrastructure and servicesAnthropic’s managed agent ecosystem, including Claude Managed Agents and the Agents APIExperience developing evaluation methodologies for LLM outputsPrevious experience within eCommerce, AI product development, workflow automation or digital agency environmentsComfortable presenting technical concepts, demonstrations and learnings to non-technical audiences

Apply for this position

This job is hosted externally. Click below to view the full posting and apply.

Apply on apply4u.co.uk

Good distractions

Talks and stories from around this role — technically off-topic, practically not.

1:00 min

Misconceptions about TypeScript safety capabilities

Simone Sanfratello · JS Congress

2:37 min

Tracing the evolution from early AI to generative AI

Mike Mike · WWC 2025

3:21 min

Navigating the ethical integration of virtual colleagues

Rudi Bauer Rudi Bauer +1 · Cappuccino with HR

1:24 min

Building client-facing AI agents for engineering teams

Alfonso Graziano Alfonso Graziano · Coffee With Developers

2:55 min

Gaining TypeScript benefits using JSDoc alternatives

Simone Sanfratello · JS Congress

40 sec

Introduction to building real-world AI agent solutions

Dennis Zielke Dennis Zielke +1 · WWC 2025

Videos

See all

Related articles

See all