The posting
About us
EggAI is a fast-growing AI consulting and development startup. We build agentic AI solutions for enterprise clients. We are growing in several European markets.
The role
You will own the design of a shared AI platform for our clients. The platform has two parts. An AI Control Plane governs what agents may do, through identity and delegated permissions, policy enforcement, approvals, budgets and durable audit records. A managed AI Runtime is where the agents run. Both integrate with the client's identity, security, delivery and audit services.
You will set the architecture, define how services and controls fit together, and make sure what the team builds is sound, assured and ready for production. The role reaches across engineering, security, audit, risk and the client's architecture function. You will take designs through their governance, record the decisions, and give the engineers a design they can build and the client a design they can approve.
You will be EggAI's accountable architecture lead on the engagement, leading design for a delivery team of platform engineers. You make the technical decisions within the team's remit, recommend on the rest, and secure the client's approval where their architecture or risk governance requires it.
What you will do
- Own the architecture of the AI Control Plane and AI Runtime and keep it aligned with the client's architecture standards, cloud substrate, API gateway, identity provider and audit services. - Define service interfaces and contracts. Decide where each security and policy control is enforced: in the gateway, the control plane, the runtime or the client's own services. - Keep the design record. Write architecture decision records (ADRs) and record every deviation from the client's standards or our reference designs for a client decision. - Take designs through the client's architecture and risk forums. Secure approvals in time for dependent work, so that design precedes implementation. - Lead design and quality review across all platform services. Review engineers' changes, cross-service tests and fault exercises with the CTO. - Define how the architecture will be proven. Agree acceptance criteria with engineers and client control owners for each interface, control and infrastructure contract, including behaviour when a dependency fails, and review the test evidence showing they are met. - Hold the build to the design's principles: policy enforced outside the agent, decisions recorded before actions take effect, fail closed with stop always available, and audit evidence that is administered independently of the people who build and run the platform, reconciled against what actually happened, and readable with the client's own tools. - Maintain the inventory of platform controls. Record for each one whether it is enforced or only monitored, whether it is implemented, tested or still open, and what evidence it produces, so acceptance reviews work from a current record and coverage gaps are visible. - Assess proposed technology, scope and dependency changes for their effect on the design, controls, effort and running costs, and give the programme lead a clear basis for plan and cost decisions. - Evaluate new runtimes and managed services against the platform's control requirements. Compare shared controls with provider-native ones on integration effort, operating cost and assurance gaps, separate what is verified from what is assumed, and recommend whether to adopt, change the design or hold scope. - Lead the technical assessment of production readiness. Review recovery, containment and fault-exercise evidence, and give the programme lead a clear view of what is ready and what is not. - Stay with the platform through go-live and the support period after it. Resolve the architectural issues that production exposes, and decide when a fix is a design change rather than a defect. - Prepare the client's receiving engineers to maintain the design. Lead the architecture parts of training and handover, and leave documentation, decision records and guidance they can extend without you.
Essential experience
- You have been the accountable solution or platform architect for systems that went into production, and have led engineers through building them. - You have delivered cloud platforms into production in a regulated environment and taken designs through formal architecture and risk governance. - You know a major cloud platform in depth: networking, identity, secrets, Kubernetes and managed services. Azure is strongly preferred. - You have hands-on experience with API gateways, identity and delegation using OAuth and OIDC, and policy as code. - You work with infrastructure as code, GitOps and software supply-chain controls, and understand how they underpin reproducible environments, conformance tests and release assurance. - You have designed systems that must produce audit evidence and fail safely: durable records, immutable storage, separation of duties and deny-by-default access. You have sound judgement about retries, partial failure, idempotency, identity propagation and recovery. - You write clear architecture decision records and can explain and defend a design to senior architects, risk owners and engineers.
Nice to have
- Delivery in financial services or banking. - LLM or agent platforms in production, including model gateways, agent orchestration and protocols such as MCP and A2A. - Audit, evidence retention or AI risk controls, including EU AI Act, PRA or FCA expectations. - Products in this space such as Kong, Open Policy Agent or Microsoft Foundry.
Practical details
- Hybrid working and client-site attendance will depend on the engagement. - You will need to complete the background and security checks required by the client.
About EggAI
Agentic workforces are inevitable. Making them work is our mission.
EggAI is building the engineering methods, operating models, and reusable technology to deploy agentic workforces with the quality and control required for sustained business impact.
Working closely with enterprise clients, we design, implement and operate agentic systems that evolve from augmenting individual tasks to autonomously executing end-to-end processes alongside people—resilient, controlled, and scalable. We begin with the client problem, select the technical approach that best serves it, and remain accountable through deployment, adoption, and operations. Each deployment strengthens the next by turning production learning into reusable capability.
We are an experienced, international team working across Europe. We set high standards, take ownership of outcomes, and value clear thinking, candid feedback, and the ability to turn ideas into tangible results.
