Agentic AI Architect
About the role
- Architecture & Design· Define and implement end-to-end AI/GenAI architecture covering:o LLM integrationRAG pipelines
- Multi-agent orchestration frameworks
- Design scalable, secure, and cost-efficient AI platforms and services
- Evaluate and select appropriate LLMs, frameworks, and toolchains
- GenAI & LLM Solutions· Design and develop GenAI-powered applications using Python and modern frameworks
- Implement:o Prompt engineering strategieso Token optimization and token economicso Response grounding and evaluation frameworks
- Integrate enterprise data sources into RAG pipelines and knowledge systems
- Agentic AI / Multi-Agent Systems· Lead design and implementation of agent-based solutions, including:o Agent design & orchestration
- Agent development and lifecycle management
- Agent hardening, testing, and evaluation
- Governance and monitoring frameworks
- Build multi-agent ecosystems with role-based and task-based agents
- Platform & Integration· Develop and expose REST APIs and microservices for AI consumption
- Implement:o Tool calling frameworkso Model Context Protocol (MCP) integrationso MCP server creation and management
- Integrate with enterprise platforms, workflows, and external APIsEngineering Excellence· Ensure best practices in:o Code quality, scalability, and performanceCI/CD for AI systems (LLMOps / MLOps)
- Security, governance, and compliance
- Collaborate with cross-functional teams (Data, Engineering, Product)
- Mandatory Skills
- Programming & Core Engineering· Strong expertise in Python
- Experience building REST APIs and scalable backend systems
- Generative AI & LLMs· Hands-on experience with:o LLM integration (OpenAI, Azure OpenAI, etc.)o Prompt engineering and optimisationo GenAI-powered application developmentRAG & Knowledge Systems· Expertise in:o RAG pipeline design & implementation
- Vector databases and semantic search
- Data chunking, indexing, and retrieval strategies
- Agentic AI· Deep experience in:o Multi-agent systems architecture
- Agent orchestration frameworks (e.g., LangGraph, CrewAI, similar)
- Agent lifecycle: design → build → evaluate → govern
- Advanced AI Concepts· Tool calling and tool orchestration
- Token usage optimisation and cost strategies
- Evaluation frameworks for GenAI outputsMCP & Advanced Integrations· Experience with:o MCP integrationo MCP server setup and management
- Context-aware AI system design
- Good to Have· Experience with LLMOps / MLOps practices
- Exposure to cloud AI platforms (Azure, AWS Bedrock, GCP Vertex AI)
- Knowledge of Graph RAG / hybrid retrieval systems
Before you apply
Applying takes about a minute. These four things decide how fast it moves after that.
Your profile is current
It's what we read first. Occupations, seniority and locations matter more than a long history.
Two examples you can talk through
Not a portfolio — just two pieces of work where you can explain the decisions and what you'd change.
A number in mind
What you're on now and what would make you move. We negotiate better when we know both.
Your notice period
Employers plan around it, and it's the question that stalls offers most often.
Once you apply, someone reads it and calls you before anything reaches the employer — usually within two working days.
