Software engineer, agents (UK)

present of AI; Greater London; Hybrid; GBP 70,000 - 110,000; Full time

Benefits offered by this job

Production Python

Agent orchestration patterns

Vector and retrieval systems

Cloud and Kubernetes

Agentic coding tools

Job summary

present of AI is seeking a fullstack engineer to build and run AI agent systems that perform multi-step tasks across enterprise tools.

The role emphasizes production Python, distributed systems, backend APIs, and wiring models with vector stores into reliable services. You will work across product, research and design to ensure observable, safe outcomes at scale.

Qualifications

• Several years of production Python experience.
• Hands-on work with distributed systems and backend APIs.
• Comfort wiring models, retrieval and vector stores into reliable services.
• Solid grounding in cloud, containers, monitoring and testing.
• Clear teamwork across product, research and design.

Responsibilities

• Build and run AI agent systems that carry out multi‑step tasks across enterprise tools.
• Develop dependable, observable, and safe agent behaviors in production.
• Integrate models with real services and ensure reliability at scale.
• Collaborate with product, research and design to shape AI decisions.

Skills

Production Python

Distributed systems

Backend APIs

Wiring models / vector stores

Cloud

Kubernetes

Testing & monitoring

Team collaboration

Tools

Vector stores

Agent toolkits

Job description

This role asks for a fullstack engineer to build and run AI agent systems that carry out multi step tasks across enterprise tools. A strong candidate brings several years of production Python, hands on work with distributed systems and backend APIs, and comfort wiring models, retrieval and vector stores into reliable services. Solid grounding in cloud, containers, monitoring and testing matters, along with clear teamwork across product, research and design.

How it fits the AI era

The work sits at the center of the shift toward agents that act on their own inside company systems, so much of the job is making those actions dependable, observable and safe. Routine coding is increasingly assisted by agentic tools, which raises the bar on design judgment, review and debugging. What stays human is deciding how agents should behave, judging tradeoffs and owning quality in production.

How it builds AI experience

A person here would gain direct practice building agent orchestration, memory, retrieval and decision logic on a platform that grounds agents in company data. That means learning how to connect models to real services and how to keep them reliable at scale. Building proof through open source agent toolkits or personal agent projects would strengthen a case for this kind of role.

Worth showing

• Production Python
• Agent orchestration patterns
• Vector and retrieval systems
• Cloud and Kubernetes
• Agentic coding tools

This is our own read, written from the employer's posting and the company's Spotlight. The employer's posting is the source of truth for the role.

About Writer

Writer is an enterprise AI platform for building and supervising AI agents grounded in company data, per the company.