Overview
The Senior Software Engineer – AI Agent Integrations will play a crucial role in developing connections between AI agent environments and enterprise systems within a UK public-sector R&D program focused on enhancing cybersecurity and operational assurance. This position involves hands-on engineering to extend existing verification capabilities and create solutions that integrate with various agent frameworks while ensuring the integrity and reliability of the evidence collected. You will collaborate closely with technical leads and other team members to build robust interfaces and integrations, effectively enabling organizations to manage and secure AI agents' interactions with their systems.
Responsibilities
- Design and build integrations with AI-agent frameworks and orchestration environments.
- Develop adapters for agent actions, tool calls, APIs, service gateways, and enterprise applications.
- Integrate relevant authentication, identity, permission, policy, and approval information.
- Implement integrations using MCP and comparable tool-interface patterns where appropriate.
- Establish clear interface contracts and observable evidence boundaries.
- Create automated integration tests and investigate behavioral differences between platforms.
- Document interface behavior, evidence limitations, configuration requirements, and coverage gaps.
- Support controlled failure, bypass, portability, and resilience testing.
Requirements
- Strong hands-on software engineering experience, particularly in Python or backend application development.
- Significant experience integrating applications or platforms through APIs, events, middleware or SDKs.
- Practical experience developing working applications using LLMs, AI agents, or tool-calling frameworks.
- Good understanding of authentication, authorization, and enterprise identity concepts.
- Experience designing and debugging integrations across multiple systems and external APIs.
- Strong automated testing and troubleshooting skills.
- Experience with cloud environments and modern software engineering practices.
- Ability to reason about provenance, security boundaries, and the reliability of information obtained through integrations.