Applied AI Engineer – LLM & Agentic Systems

About the Opportunity

AIDA Recruitment is looking for an experienced Applied AI Engineer to join our client's rapidly growing, AI-native technology company in the UK.

Our client is transforming the property management industry by developing an AI-powered platform that automates complex operational processes, integrates traditional businesses, and improves efficiency at scale.

Following a $170 million Series B funding round , the company has raised more than $260 million and now manages over 15,000 properties across the UK.

You will join a growing engineering organization of approximately 20 people, working in small, autonomous teams of 2–3 engineers.

This is an opportunity to become an early core contributor to the company's agentic AI infrastructure, influence architectural decisions, and develop systems already supporting real business operations.

This is not an AI research or traditional Machine Learning position. We are looking for a strong backend software engineer who has built, deployed, and maintained AI agents in production.

Location: Fully Remote – UK & Europe (UK working hours)

Salary: €100,000–€150,000 annually

Contract: Full-time | Permanent or B2B

Equity: Competitive equity options

Tech Stack: TypeScript, Node.js, PostgreSQL, Python, LLMs, Agentic AI

Visa sponsorship: Sponsorship or visa transfers may be possible for candidates already based in London. New international relocation is not offered as standard.

Key Responsibilities

AI Agent Development & Architecture

• Design, build, and maintain production-grade LLM-powered agents and multi-agent systems.
• Develop agentic workflows involving task decomposition, tool calling, structured outputs, orchestration, and feedback loops.
• Build reusable agent components, including memory, context management, and tool integrations.
• Design scalable architectures connecting AI agents with backend services, databases, and business applications.
• Establish architectural patterns that allow new AI workflows to be introduced efficiently.

Evaluation, Reliability & Performance

• Design and implement automated evaluation frameworks for AI agents.
• Create evaluation datasets with measurable success criteria and pass thresholds.
• Integrate agent evaluations into CI/CD pipelines and release processes.
• Monitor and improve agent reliability, latency, accuracy, and operational costs.
• Investigate hallucinations, incorrect tool calls, unexpected outputs, and production failures.
• Develop observability, debugging, error-handling, and fallback mechanisms.

Product Development & Engineering

• Collaborate with product managers, data engineers, and operational teams to identify automation opportunities.
• Transform complex business processes into reliable AI-driven solutions.
• Take ownership of features from architecture and development through deployment and production monitoring.
• Use modern AI coding agents, such as Claude Code or Codex, to improve engineering productivity.
• Contribute to technical decisions, engineering standards, and long-term platform scalability.

Essential Requirements

Software Engineering Background

• 3+ years of professional software engineering experience , with strong backend development expertise.
• Hands-on experience with TypeScript/Node.js , or strong Python backend experience with willingness to work in a TypeScript-first environment.
• Experience designing APIs, integrating databases, and building scalable production applications.
• Strong understanding of software architecture, testing, CI/CD, and production reliability.
• Bachelor's degree in Computer Science or a related technical field.

Production AI & Agentic Systems – Mandatory

• Proven experience personally building and deploying LLM-powered agents or agentic systems used by real users in production.
• Hands-on experience with agent orchestration, tool calling, structured outputs, context management, and feedback loops.
• Ability to explain the complete architecture of an AI system you developed, including your individual technical contributions.
• Experience handling real production challenges involving latency, cost, reliability, hallucinations, and failure recovery.
• Practical experience building agent evaluations, including evaluation datasets, measurable success thresholds, and automated testing or release gates.
• Understanding of when to use LLMs, deterministic software, multiple agents, or human intervention.

Professional Background & Mindset

• Recent hands-on engineering experience in an AI-native company, product-led startup, or high-growth technology scale-up is strongly preferred.
• Experience independently owning and delivering production software systems.
• Strong problem-solving abilities and architectural judgment.
• Entrepreneurial mindset with the ability to work independently in a fast-paced environment.
• Excellent English communication skills.

Nice-to-Have Experience

• Developing reusable agent orchestration frameworks or shared AI engineering libraries.
• Building production multi-agent systems with specialized subagents.
• Experience with PostgreSQL and distributed backend architectures.
• Implementing advanced LLM observability and evaluation tools.
• Optimizing LLM inference costs, response latency, and system performance.
• Previous experience in an early-stage, AI-focused product engineering team.

What Kind of Experience Are We Looking For?

We are particularly interested in engineers who can demonstrate ownership of real production AI systems.

A strong candidate should be able to describe

• A production AI agent: What did you build, what business problem did it solve, and how many users or transactions did it support?
• System architecture: How did you implement agent orchestration, tool integration, context management, and backend services?
• Evaluation: How did you measure agent quality? What evaluation dataset sizes, pass thresholds, or automated release checks did you use?
• Production challenges: What specific failure,