AI Full Stack Engineer – LLMs, Python & Agentic AI

Cedar Recruitment; Greater London; Hybrid; GBP 63,000 - 77,000; Full time

Job summary

Cedar Technology is recruiting an AI Full Stack Engineer to help an investment organisation undergo an ambitious AI transformation. You will join a small, influential AI team and work directly with senior stakeholders to design, develop and deploy intelligent applications across the business.

You’ll own the end-to-end AI engineering lifecycle, building agentic AI applications, integrating with enterprise data, and evaluating model performance while collaborating with IT and data teams.

Qualifications

• Strong Python programming and broader full stack engineering capability.
• Demonstrable experience building and shipping software products that people rely on, including AI or agentic applications.
• Practical understanding of LLMs, generative AI and modern AI development techniques.
• Experience with prompt engineering, RAG, embeddings or agent-based workflows.
• Understanding of model evaluation, reliability and AI deployment security considerations.
• Confidence making technical architecture decisions and explaining the reasoning behind them.
• Ability to own problems from discovery through delivery and iteration.
• Strong communication skills and ability to work with non-technical stakeholders.

Responsibilities

• Building agentic AI applications: design and develop intelligent agents, multi-step workflows and AI-powered tools that automate complex business processes.
• Engineering LLM-powered solutions: develop production-ready applications using modern language models, including Anthropic’s Claude ecosystem.
• Developing AI integrations: build and evaluate integrations using MCP, APIs and enterprise data sources.
• Designing retrieval and context systems: apply RAG, embeddings, prompt engineering to improve accuracy and usefulness of AI applications.
• Establishing evaluation and reliability: implement testing, guardrails and monitoring for expected behavior.
• Connecting AI with enterprise data: collaborate with data and IT teams to integrate AI with Microsoft technologies, Azure and Fabric.
• Influencing technical architecture: contribute to tool choices, security, scalability and build-versus-buy decisions.
• Driving AI adoption: work with non-technical teams to identify opportunities and deliver usable AI solutions.

Skills

Python programming

Full stack engineering

LLMs / Generative AI

Prompt engineering

RAG / embeddings

Technical architecture

Ownership & delivery

Communication with stakeholders

Tools

Anthropic Claude

Claude Code

MCP (Model Context Protocol)

Microsoft Azure

Azure Fabric

SharePoint

Graph API

Power Automate

Job description

AI Full Stack Engineer – LLMs, Python & Agentic AI

Location: London (Hybrid, 2-3 days per week in the office)

Salary: Up to £70,000 a year DOE.

Employment Type: Permanent, Full Time

Sector: Investment Technology

Build the AI capabilities of an organisation, not just another chatbot.

What if you could help an established investment organisation fundamentally rethink how it operates through artificial intelligence?

Cedar Technology is recruiting for an AI Full Stack Engineer opportunity within an investment organisation undergoing an ambitious AI transformation.

Rather than joining a large engineering function to maintain existing systems, you’ll become part of a small, highly influential AI team, working directly with senior stakeholders to design, develop and deploy intelligent applications across the business.

The organisation is investing in becoming AI native, with opportunities spanning investment processes, enterprise automation, data workflows and the wider application of agentic AI.

This is a role for someone who wants to build, experiment, influence technical strategy and take genuine ownership of what they deliver.

You’ll work across the full AI engineering lifecycle, from identifying valuable use cases and making architectural decisions through to building, deploying and improving systems that people actually use.

The engineering challenge

You’ll work closely with the Head of AI, contributing both hands‑on engineering expertise and technical judgement to a growing portfolio of AI initiatives.

Your responsibilities will include:

• Building agentic AI applications: Design and develop intelligent agents, multi-step workflows and AI-powered tools that automate complex business processes.
• Engineering LLM-powered solutions: Develop production-ready applications using modern language models, including Anthropic’s Claude ecosystem.
• Developing AI integrations: Build and evaluate integrations using Model Context Protocol (MCP), APIs and enterprise data sources.
• Designing retrieval and context systems: Apply RAG, embeddings, prompt engineering and context engineering to improve the accuracy and usefulness of AI applications.
• Establishing evaluation and reliability: Implement appropriate testing, evaluations, guardrails and monitoring to ensure applications behave as expected.
• Connecting AI with enterprise data: Work alongside data and IT teams to integrate AI capabilities with Microsoft technologies, Azure and Fabric.
• Influencing technical architecture: Contribute to decisions involving AI tooling, vendor selection, security, scalability and build-versus-buy considerations.
• Driving AI adoption: Collaborate with non-technical teams to identify opportunities, develop useful solutions and help colleagues use AI effectively.

What we’re looking for

We’re interested in engineers who combine strong software engineering fundamentals with practical experience developing and deploying AI applications.

Core requirements

• Strong Python programming and broader full stack engineering capability.
• Demonstrable experience building and shipping software products that people genuinely rely on, including AI or agentic applications.
• Practical understanding of LLMs, generative AI and modern AI development techniques.
• Experience with prompt engineering, RAG, embeddings or agent-based workflows.
• An understanding of model evaluation, reliability and the security considerations involved in AI deployment.
• Confidence making technical architecture decisions and explaining the reasoning behind them.
• Ability to take ownership from initial problem discovery through to delivery and iteration.
• Strong communication skills and the ability to work directly with non-technical stakeholders.

Particularly interesting experience

• Anthropic Claude, Claude Code or other AI-assisted development environments.
• Model Context Protocol (MCP), tool calling and agent orchestration.
• Microsoft Azure, Fabric, SharePoint, Graph API or Power Automate.
• AI evaluation frameworks, guardrails and context management.
• Enterprise automation, data pipelines and API integrations.
• Experience working in a small engineering team with significant autonomy.

You don’t need to have worked with every technology listed.

We’re more interested in your technical foundations, capacity to learn and evidence that you can take an emerging technology from experimentation into practical use.

Why consider this opportunity?

1. Genuine technical ownership

You’ll have the opportunity to influence architectural decisions, select tools and help establish how AI is developed and deployed across the organisation.

2. Work with emerging AI technology

The remit includes LLMs, agentic workflows, MCP integrations, AI-assisted software development and the practical challenges of implementing reliable intelligent systems.

3. Visibility and influence

Working within a small AI team means collaborating closely with business leaders and influencing initiatives that extend across multiple functions.

4. An organisation investing in AI transformation

This is an opportunity to help an established business evolve its operating model around new technological capabilities, rather than simply adding AI features to an existing product.

5. Work with a purpose

Your engineering expertise will contribute to an organisation operating within investment, connecting advanced technology with work intended to generate positive outcomes.

Why Cedar Technology?

At Cedar Technology, we specialise in recruiting across Applied AI, Machine Learning, AI Engineering and ML Infrastructure.

We understand the difference between engineers who have experimented with LLM APIs and those who can design, build and maintain intelligent systems that deliver dependable results.

Our approach focuses on six key areas through our PROVEN assessment framework:

• Production Experience: Have you deployed AI systems into real-world environments?
• Results Delivered: What measurable outcomes have your solutions achieved?
• Ownership: Which architectural and engineering decisions were genuinely yours?
• Validation of Experience: Can you demonstrate the depth of your technical understanding?
• Engineering Execution: How do you approach reliability, evaluation, security and scalability?
• Needs Alignment: How does your experience translate to the organisation’s engineering challenges?

We believe exceptional AI Engineers should be assessed on their ability to solve real problems, not simply the number of frameworks listed on their CV.

Candidates must have the existing right to work in the UK. Visa sponsorship is not available for this opportunity.

Cedar Recruitment Limited is acting as a recruitment agency in relation to this permanent vacancy.

Tagged as: Agentic AI, AI Agents, AI Engineering, AI Eval, Anthropic, Claude, Claude Code, Context Engineering, Full Stack Engineering, GenAI, Generative AI, Large Language Models, LLMs, MCP, Model Context Protocol, Prompt Engineering, Python, RAG, Retrieval Augmented Generation