Senior AI Engineer (Amazon Bedrock)

Key Responsibilities

• check_circle Design and implement production agentic AI systems on Amazon Bedrock, including multi-agent orchestration, memory management, and tool integration using Amazon Bedrock AgentCore and Strands Agents
• check_circle Build, integrate, and maintain MCP (Model Context Protocol) servers that expose capabilities to AI agents across client platforms
• check_circle Architect and implement RAG pipelines using Amazon Bedrock Knowledge Bases, managing vector stores, embeddings, and document ingestion from S3 and other sources
• check_circle Apply the A2A (Agent-to-Agent) protocol to enable interoperability between agents across systems and workflows
• check_circle Instrument AI systems with observability and tracing tooling — CloudWatch, spans, and traces — to support debugging, performance monitoring, and compliance requirements
• check_circle Integrate LLMs into client applications through prompt engineering, context management, and function/tool calling patterns
• check_circle Leverage serverless infrastructure — AWS Lambda, DynamoDB, S3 — to build scalable, cost-efficient backends for AI workloads
• check_circle Collaborate with client engineering and product teams to translate requirements into agent architectures, contributing to technical roadmaps and AI strategy

Skills & Experience

• Amazon Bedrock at scale — hands-on implementation of agents, knowledge bases, and model inference in production environments, not limited to basic API calls
• Agentic AI and multi-agent systems — direct experience designing and deploying agent pipelines with real orchestration complexity
• MCP (Model Context Protocol) — built or integrated MCP servers in a production or near-production context
• Strands Agents — familiarity with the framework and its application to agentic workflows on AWS
• RAG implementation — knowledge base design, chunking strategy, vector store configuration, and retrieval evaluation
• Python — strong, applied proficiency in an AWS and AI context
• AWS infrastructure — working knowledge of Lambda, DynamoDB, and S3 as components of AI system backends
• Observability — experience instrumenting AI systems with tracing, logging, and monitoring tooling (CloudWatch preferred)
• LLM integration — prompt engineering, tool/function calling, context window management, and output parsing
• AWS certifications desirable, particularly the AI/ML Specialty

Our UK Benefits

• check_circle 35 days leave (including bank holidays).
• check_circle Private medical insurance.
• check_circle Enhanced parental and adoption leave.
• check_circle Financial coaching + 5% pension match.
• check_circle 40 hours of paid learning and development.

About the company