Senior AI Software Engineer

Ocho; Belfast City District; On-site; GBP 90,000 - 140,000; Full time

Benefits offered by this job

Share options

Job summary

Ocho is seeking a Senior Backend Engineer to build the core of an AI operating system. This role focuses on platform engineering rather than model research, delivering scalable services that power intelligent applications.

You will own orchestration layers, retrieval infrastructure, evaluation pipelines and reliability, deploying on AWS with Java/Go and Python in a fast-moving team.

Qualifications

• 5+ years building production backend systems.
• Strong in Java or Go, plus working Python.
• Hands-on experience integrating large language models into production software.
• Solid cloud experience, ideally AWS.
• Comfortable with distributed systems and microservice architectures.
• Eligible for UK security clearance.

Responsibilities

• Design and build core backend services underpinning the AI platform.
• Build and maintain LLM integration and agent orchestration layers.
• Develop retrieval infrastructure across graph and vector stores.
• Own performance, reliability and observability of the services you build.
• Deploy and operate services on AWS.
• Build automated evaluation into the delivery pipeline.
• Review code and raise the technical bar across the team.
• Mentor mid-level engineers as the team grows.

Skills

Backend systems

Java

Go

Python

LLM integration

AWS

Distributed systems

Microservice architectures

Agent orchestration

Tools

Neo4j

Job description

• Senior backend role building the core of an AI operating system


• Java, Go and Python across LLM integration, agent orchestration and retrieval infrastructure


• AWS, Neo4j, distributed systems at real scale


• Platform already live and in daily operational use with major customers


• Share options and an engineering culture built around AI tooling

About the Company

My client is a UK technology company building an AI operating and orchestration layer that puts intelligent systems to work inside large, complex organisations where accuracy and accountability really matter. The platform is already live and in daily operational use with major customers. The engineering group is small, senior and unusually fast moving, with AI tooling built into how the team genuinely works rather than bolted on afterwards.

The Role

This is core platform engineering rather than model research. You will build the services that make AI usable at scale: orchestration layers, retrieval infrastructure, evaluation pipelines and the plumbing that keeps it all reliable in constrained environments. The codebase is modern, the team is senior, and there is very little between deciding something and shipping it. It suits an engineer who wants to build AI infrastructure properly rather than assemble it from tutorials.

Key Responsibilities

• Design and build core backend services underpinning the AI platform


• Build and maintain LLM integration and agent orchestration layers


• Develop retrieval infrastructure across graph and vector stores


• Own performance, reliability and observability of the services you build


• Deploy and operate services on AWS


• Build automated evaluation into the delivery pipeline


• Review code and raise the technical bar across the team


• Mentor mid-level engineers as the team grows

What You\'ll Need

• 5+ years building production backend systems


• Strong in Java or Go, plus working Python


• Hands-on experience integrating large language models into production software


• Solid cloud experience, ideally AWS


• Comfortable with distributed systems and microservice architectures


• Eligible for UK security clearance

Desirable / Nice to Have:

• Neo4j or another graph database in production


• Experience with agent frameworks or LLM evaluation tooling

Why Apply?

• Build AI infrastructure that is genuinely in operational use


• Modern stack with no meaningful legacy drag


• Share options as part of the package


• AI development tooling expected and actively encouraged


• Senior team where technical arguments are decided on merit


• Strong progression as the platform and customer base expand