MRI India
We are seeking a Senior Enterprise Architect (AI Focused) to lead our enterprise AI strategy and drive the design of scalable, cloud native AI solutions. The role focuses on agentic AI, multi agent systems, RAG architectures, and enterprise AI integration aligned to business goals. It establishes best practices for AI architecture, orchestration, governance, and responsible AI, partnering with cross functional teams to deliver secure, production grade solutions across the organisation. The working model is hybrid: 3 days working from home per week, based in the London office, open to UK remote candidates. Key Responsibilities Define and lead the enterprise AI architecture strategy, aligning agentic AI capabilities with business goals Design and govern scalable AI architectures, including multi agent systems, data pipelines, and model lifecycle management Drive adoption of agentic AI frameworks and establish best practices for orchestration, tool usage, and system integration Architect and oversee RAG based solutions, ensuring effective retrieval pipelines, embedding strategies, and knowledge integration Lead integration of AI solutions across enterprise platforms, APIs, and third party services Establish standards for prompt engineering, multi step orchestration, and agent behaviour design Ensure robust governance, including security, compliance, auditability, and responsible AI practices Collaborate with engineering, data, and business teams to deliver production grade AI systems Provide technical leadership across cloud native AI platforms, particularly within Azure ecosystems Mentor teams on AI architecture patterns, emerging technologies, and implementation strategies Must Have Skills & Experience Agentic AI Frameworks: LangChain, LangGraph, Microsoft Agent Framework (formerly AutoGen / Semantic Kernel), CrewAI Databases: SQL (e.g., PostgreSQL) for configuration & operational data; NoSQL vector databases (e.g., Azure Cosmos DB) for embeddings & retrieval Azure Platform: Azure AI Foundry, Azure OpenAI Service, Azure AI Services, Azure App Service, Azure AI Technologies RAG Architectures: chunking strategies, embedding models, retrieval pipelines Python for agent development, ML techniques, APIs Prompt engineering, system prompt design, tool/function calling patterns, multi step orchestration API Integration: calling and orchestrating third party APIs for agent tool use Knowledge of C# API development and DevOps CI/CD pipelines (Azure DevOps or GitHub Actions) Docker, Infrastructure as Code (Terraform or Bicep) Frontend integration: Angular or React for agent facing UIs or dashboards MCP (Model Context Protocol) integration; MCP Apps for interactive UI components Observability & evaluation: LangSmith or similar tracing/evaluation tools; streaming & real time responses (SSE, WebSockets) Testing non deterministic AI outputs, evaluation strategies, golden datasets, regression testing Cost management & token budgeting, caching strategies Multi agent orchestration: collaborative agent systems with delegation and handoffs Fine tuning / model customization for domain specific use cases Authentication & identity: OAuth, managed identities; logging & audit trails for compliance and traceability Experience with additional LLM providers beyond Azure OpenAI (e.g., Anthropic, open source via Ollama/vLLM) Graph databases (Neo4j or similar) for knowledge graph backed agents; message queues & event driven architecture (Azure Service Bus) Security & guardrails: content filtering, prompt injection mitigation, PII handling API design: REST or GraphQL for exposing agent capabilities Benefits Hybrid working model - 3 days from home per week, based in London office (remote accepted within UK) 25 days of annual leave plus bank holidays; 6 early finish days per year as part of Flexi scheme Private medical insurance and health cash plan for employees and families Competitive personal pension plan and tuition reimbursement schemes Income protection plans and generous parental leave and support perks Flexibility to work from anywhere in the world for two weeks a year
We are seeking a Senior Enterprise Architect (AI Focused) to lead our enterprise AI strategy and drive the design of scalable, cloud native AI solutions. The role focuses on agentic AI, multi agent systems, RAG architectures, and enterprise AI integration aligned to business goals. It establishes best practices for AI architecture, orchestration, governance, and responsible AI, partnering with cross functional teams to deliver secure, production grade solutions across the organisation. The working model is hybrid: 3 days working from home per week, based in the London office, open to UK remote candidates. Key Responsibilities Define and lead the enterprise AI architecture strategy, aligning agentic AI capabilities with business goals Design and govern scalable AI architectures, including multi agent systems, data pipelines, and model lifecycle management Drive adoption of agentic AI frameworks and establish best practices for orchestration, tool usage, and system integration Architect and oversee RAG based solutions, ensuring effective retrieval pipelines, embedding strategies, and knowledge integration Lead integration of AI solutions across enterprise platforms, APIs, and third party services Establish standards for prompt engineering, multi step orchestration, and agent behaviour design Ensure robust governance, including security, compliance, auditability, and responsible AI practices Collaborate with engineering, data, and business teams to deliver production grade AI systems Provide technical leadership across cloud native AI platforms, particularly within Azure ecosystems Mentor teams on AI architecture patterns, emerging technologies, and implementation strategies Must Have Skills & Experience Agentic AI Frameworks: LangChain, LangGraph, Microsoft Agent Framework (formerly AutoGen / Semantic Kernel), CrewAI Databases: SQL (e.g., PostgreSQL) for configuration & operational data; NoSQL vector databases (e.g., Azure Cosmos DB) for embeddings & retrieval Azure Platform: Azure AI Foundry, Azure OpenAI Service, Azure AI Services, Azure App Service, Azure AI Technologies RAG Architectures: chunking strategies, embedding models, retrieval pipelines Python for agent development, ML techniques, APIs Prompt engineering, system prompt design, tool/function calling patterns, multi step orchestration API Integration: calling and orchestrating third party APIs for agent tool use Knowledge of C# API development and DevOps CI/CD pipelines (Azure DevOps or GitHub Actions) Docker, Infrastructure as Code (Terraform or Bicep) Frontend integration: Angular or React for agent facing UIs or dashboards MCP (Model Context Protocol) integration; MCP Apps for interactive UI components Observability & evaluation: LangSmith or similar tracing/evaluation tools; streaming & real time responses (SSE, WebSockets) Testing non deterministic AI outputs, evaluation strategies, golden datasets, regression testing Cost management & token budgeting, caching strategies Multi agent orchestration: collaborative agent systems with delegation and handoffs Fine tuning / model customization for domain specific use cases Authentication & identity: OAuth, managed identities; logging & audit trails for compliance and traceability Experience with additional LLM providers beyond Azure OpenAI (e.g., Anthropic, open source via Ollama/vLLM) Graph databases (Neo4j or similar) for knowledge graph backed agents; message queues & event driven architecture (Azure Service Bus) Security & guardrails: content filtering, prompt injection mitigation, PII handling API design: REST or GraphQL for exposing agent capabilities Benefits Hybrid working model - 3 days from home per week, based in London office (remote accepted within UK) 25 days of annual leave plus bank holidays; 6 early finish days per year as part of Flexi scheme Private medical insurance and health cash plan for employees and families Competitive personal pension plan and tuition reimbursement schemes Income protection plans and generous parental leave and support perks Flexibility to work from anywhere in the world for two weeks a year