Platform Architect

Capital.com is building out its internal platform capabilities with a growing focus on AI, serving more than 1,000 employees.

• 8+ years engineering experience with at least 2 years building production LLM-based systems.
• Ability to operate independently as the first person in a function, setting priorities and delivering without a team.
• Production-grade Python development skills.
• Deep experience with Anthropic and/or OpenAI APIs including function calling, tool use, streaming, RAG, prompt management, token optimization, and model versioning.
• Experience with agentic platforms, MCP servers, and gateways designing AI agent service flows.
• Experience deploying and securing multi-step automation with n8n at organizational scale.
• Strong AWS skills for AI workloads including Bedrock, SageMaker, Lambda, S3, IAM, and CloudWatch.
• Strong GCP skills for AI workloads including Vertex AI, Cloud Functions, Cloud Storage, IAM, and Cloud Monitoring.
• Hands-on DevOps capability for deployment and operation.
• Architectural thinking with end-to-end design, trade-off documentation, and ability to defend decisions.
• Security engineering including secrets management, key rotation, and least-privilege IAM.
• Data protection and auditability by design including classification, controls, logging, and audit trails.
• Knowledge of LLM threat surfaces and frameworks such as OWASP LLM Top 10 or NIST AI RMF.

• Build the AI platform architecture including access, governance, monitoring, and extension of LLM capabilities.
• Own architectural decisions for the AI platform and provide documentation and justification.
• Evaluate and select new models, tools, and frameworks.
• Deliver the platform as a service for teams to deploy agents into governed cloud infrastructure.
• Govern API access, credential management, model version policies, cost allocation, and use standards for Anthropic, OpenAI, and future providers.
• Manage technical relationships with Anthropic and OpenAI.
• Build cloud infrastructure for AI workloads on AWS and GCP including Bedrock, SageMaker, Vertex AI, Cloud Functions, S3, Cloud Storage, IAM, and monitoring.
• Deploy and securely configure n8n, build automation workflows connecting LLMs to Jira, Confluence, Slack, Google Workspace, HR systems, and proprietary data.
• Design and secure MCP servers and gateways for AI agent connections.
• Build Python integrations for AI tooling including RAG pipelines, agent frameworks, prompt libraries, and internal AI assistants.
• Write code, build workflows, and deploy tooling hands-on.
• Build data privacy and security architecture for LLM usage complying with FCA, CySEC, ASIC, and DORA regulations.
• Build observability tools for token consumption, costs, latency, errors, and policy violations.
• Develop an AI adoption framework with standards, patterns, and onboarding materials.
• Conduct internal enablement through workshops, documentation, and direct team support.
• Report AI platform status, risks, and roadmap to Technology leadership.