AI Agent Engineer

AI Agent Engineer
Location: Fully remote (EU)
Level: Mid to Senior
Type: Permanent, flexible working




The Role
We're looking for an AI Agent Engineer to design, build and orchestrate production multi-agent systems. This is a hands-on engineering role - you'll be architecting agent workflows, integrating tooling, and shipping them into a live product used at scale.
This is not a prompt-tuning role. We need someone who has taken agentic systems into production and dealt with the reality of that: state management, tool reliability, error handling, and everything that breaks when an agent has to run for more than one turn.
You'll need a genuine software engineering background. The agent work is the interesting part, but you're an engineer first.




What You'll Be Doing

Designing and building multi-agent systems that run in production, not proof-of-concept
Implementing tool and function calling, structured outputs, and MCP or comparable tool-integration standards
Managing context at scale - retrieval pipelines, memory, and long-running task state
Prompt engineering and iterating on agent performance with real usage data
Building and maintaining the surrounding application - APIs, front end, data layer
Owning deployment and monitoring on cloud infrastructure
Working closely with product to translate messy real-world workflows into reliable automated ones




What We're Looking For
Essential


Demonstrable production experience building and orchestrating multi-agent systems, not just single-prompt integrations
Working knowledge of at least one agent framework - LangGraph, CrewAI, AutoGen, n8n, OpenClaw or equivalent
Practical experience with tool/function calling, structured outputs, and MCP or comparable tool-integration standards
Prompt engineering and context management at scale, including retrieval and long-running task state
Strong development background across JavaScript/TypeScript, Node.js, React and Next.js
Working knowledge of MySQL or comparable relational databases
Experience with AWS services - Amplify, Elastic Beanstalk/ECS, RDS, S3, CloudWatch

Nice to Have


Experience evaluating and testing agent behaviour (evals, tracing, observability)
Exposure to fine-tuning, embeddings or vector databases
Background in a regulated or high-accuracy domain where getting it wrong has consequences




What We Offer

Fully remote across the EU
Genuinely flexible working
Real ownership of an AI product that's already live
Mid to senior level, with scope to grow into technical leadership