AI Engineer
About The RoleWe are actively building diverse teams and welcome applications from everyone.Role: AI EngineerLocation: Birmingham (SCC operate hybrid working, which comprises of a mix of office and home working)Contract Type: PermanentSalary Package: Competitive base salary plus large company benefits, a broad flexible benefits scheme, and 2 paid-for volunteering days a yearHours: 9.00 am – 5.30 pm Monday – FridayInterview Process: 3-stage processWhy SCC An inclusive workplaceExcellent package: solid basic and company benefitsHybrid working & core hours in line with role requirementsCareer development and life-long learning opportunitiesOpportunity to join Europe's largest privately-owned IT CompanyRole purpose: We are looking for an AI Engineer to design, build, and maintain AI-powered systems across SCC. This is a broad and evolving role, the nature of the work will vary by initiative. One project may call for an AI agent that orchestrates data sources and tools; another may require a Retrieval-Augmented Generation (RAG) system over internal knowledge; another may be an AI layer embedded into an existing business process or platform. What stays consistent across all of it is the approach: working with best-in-class foundation models via API, integrating cleanly with enterprise data and systems, and building things that work reliably in production — not just in a demo. You will work closely with the Data Science team who supply clean, structured data, and with MLOps who handle deployment and infrastructure. You will also engage directly with business stakeholders to understand problems before proposing AI solutions. Security clearance or willingness to apply will be required for this role.Key responsibilities:Design and build the appropriate AI solution for each initiative, whether that is an agent, a RAG pipeline, a document processing system, or something elseIntegrate foundation models (via API) into business applications and workflowsDevelop MCP (Model Context Protocol) servers and tool integrations where agent-based approaches are appropriateBuild RAG pipelines that surface accurate, attributed answers from internal knowledge and data sourcesTransform AI capabilities into APIs and microservices that connect with existing enterprise platformsBuild prompt engineering frameworks that produce structured, reliable, and auditable outputsImplement context management, tool routing, and retrieval patterns that control what the model sees and whenCollaborate with Data Scientists to ensure clean, trusted data enters every AI systemTest and validate AI system behaviour across real use cases; iterate based on production feedbackEnsure all AI outputs are transparent, traceable, and compliant with governance requirementsDocument system behaviour, data flows, tool calls, and decision logic thoroughlyWork with product and business teams to embed AI into existing workflowsSupport AI adoption and share best practices across SCCSkills and experience:AI System Design• Selecting the right AI pattern for the problem — agent, RAG, pipeline, classifier, or hybrid
- AI agent architecture and multi-step workflow orchestration
- Retrieval-Augmented Generation (RAG) design and implementation
- Document processing and knowledge extraction systems
- Working with foundation models via API (e.g. Azure OpenAI, OpenAI)
- Prompt engineering for structured, grounded, and reliable outputs
- Context management, chunking strategies, and retrieval optimisation
- Hallucination mitigation and source attribution by design• Experience building and shipping more than one type of AI system
- Strong proficiency in Python and REST API development
- Building APIs and microservices to expose AI capabilities
- Integrating AI systems with enterprise tools and data sources
- Secure API integration (OAuth, API keys, credential management)
- Software engineering best practices, testing, versioning, documentation
- Understanding of enterprise data flows and system architecture
- Evaluating AI system performance and identifying failure modes
- Understanding of AI risk, bias, and transparency obligations
- Familiarity with AI governance frameworks (e.g. EU AI Act)
- Clear documentation of system behaviour, inputs, outputs, and limitations
- Cross-functional collaboration with data scientists, MLOps, and product teams
- Ability to push back on AI for its own sake and advocate for the right solution
- Championing best practices and supporting AI adoption across the organisation