Principal Software Engineer

RedRock Resourcing; Reading; On-site; GBP 110,000 - 160,000; Full time

Job summary

Agentic Engineering is seeking a Principal Software Engineer to lead AI-driven modernisation of complex legacy systems. You will shape the engineering harness and governance around AI agents, work across architecture and developer experience, and drive high-quality, scalable software delivery.

You’ll collaborate with teams to implement automated testing, evals and robust guardrails, ensuring safe, rapid evolution of critical codebases using Claude Code, MCP and other agentic tools.

Qualifications

• Strong software engineering foundation, especially in C#/.NET.
• Experience with large, complex or legacy systems.
• Knowledge of AI-assisted software development and agentic tooling.

Responsibilities

• Use AI coding agents to investigate, refactor and modernise legacy codebases.
• Design the 'engineering harness' that gives AI agents context, rules and constraints.
• Build repository-level instructions, agent skills, prompts and dynamic context.
• Establish automated testing and AI evaluation frameworks to ensure quality.
• Build guardrails, sandboxes and CI/CD controls around AI-driven development.

Skills

C#/.NET

AI & agentic engineering

Tools

Claude Code

MCP

GitHub Copilot

Codex

Cursor

Job description

Principal Software Engineer – Agentic Engineering

Using AI and agentic engineering to modernise complex legacy software, and fundamentally change how engineering teams build software.

This isn't a traditional software engineering role.

You won't simply be picking up tickets, writing code and moving onto the next sprint.

You'll be working at the intersection of software engineering, architecture, AI, developer experience and legacy modernisation, helping to design the systems, standards and guardrails that allow engineers to deliver better software safely.

What will you actually be doing?

• Use AI coding agents to investigate, refactor and modernise legacy codebases


• Design the "engineering harness"\ that gives AI agents the right context, rules and constraints to work effectively


• Build repository-level instructions, agent skills, prompts and dynamic context


• Work with technologies such as Claude Code, MCP and other agentic development tools


• Establish automated testing and AI evaluation frameworks (evals) to make sure speed doesn't come at the expense of quality


• Build guardrails, sandboxes and CI/CD controls around AI-driven development

What background are we looking for?

We're looking for someone who has built a seriously strong software engineering foundation.

You’ll ideally have deep experience in C#/.NET, alongside experience working with large, complex or legacy systems.

You might have worked with:

• Claude Code, Cursor, GitHub Copilot, Codex or similar coding agents


• Agentic development or AI-assisted software engineering


• Automated testing, evals and quality frameworks


• Legacy modernisation, major refactoring or framework migrations

You’ll be joining during a major transformation across Technology, with significant investment in:

• Public cloud migration


• AI-enabled software engineering