AI Engineer (Global)

Minimum Requirements

• Build reliable workflows using structured outputs, tool calling, routing, budget controls and human approval when required.
• Design and deploy agentic AI systems using leading model providers, including Anthropic, Azure OpenAI, Google Vertex AI and open-source models.
• Develop document and knowledge-processing solutions for PDFs, scans, spreadsheets and internal documentation, including extraction, validation, search and citation capabilities.
• Integrate AI solutions with company systems such as email, shared drives, CRM, ERP, internal databases and external APIs.
• Transform prototypes into reliable production services using containerisation, CI/CD, logging, monitoring and operational runbooks.
• Develop and maintain evaluation frameworks, reference datasets, regression tests and quality metrics for AI systems.
• Monitor model usage, token consumption, cost and performance, implementing alerts when quality or expenditure deviates from expected levels.
• Apply security-by-design principles, including least-privilege access, secure secrets management, prompt-injection protections and appropriate data governance.
• Ensure AI solutions are developed in line with relevant data protection and AI regulations, including GDPR and the EU AI Act.
• Partner with business teams to identify and assess automation opportunities, determining when to use traditional software, AI solutions or alternative approaches.
• Develop reusable libraries, templates and internal AI guidelines.
• Provide support and practical training to colleagues using AI tools.
• Document technical decisions and maintain agreed interfaces, schemas and architecture standards.

Key Responsibilities

• Minimum 7 years of software engineering experience, including hands-on experience deploying LLM-based solutions used in production environments.
• Strong Python skills, including typing, Pydantic, testing frameworks such as pytest and modern dependency management tools.
• Direct experience working with AI provider SDKs and concepts such as structured outputs, tool calling, prompt caching and token management.
• Strong understanding of AI evaluation methodologies, quality measurement and regression testing.
• Experience with Docker, CI/CD, cloud infrastructure, logging and monitoring.
• Strong data engineering fundamentals, including SQL, APIs, schema management, data pipelines and formats such as Parquet.
• Experience managing AI systems with defined cost and resource constraints.
• Strong understanding of security considerations for LLM-based systems and responsible tool access.
• Ability to communicate technical limitations and recommendations clearly to non-technical stakeholders.
• Professional English for technical documentation, code and communication.

If you have not had any response within one week, please consider your application unsuccessful. Your CV will be kept on file for any further suitable positions.