Role: Principal AI Architect
If the following job requirements and experience match your skills, please ensure you apply promptly.
Location: London, UK
Hybrid: 3 days a week from office
Job Description : Principal AI Architect to lead the design and implementation of enterprise-scale AI solutions for financial services automation. Drive architectural decisions for LLM-based systems, agentic workflows, and intelligent document processing platforms serving private equity and fund management operations.
Required Qualifications
15+ years of experience in AI/ML architecture with 8+ years in enterprise AI solutions
Deep expertise in LLM architectures, prompt engineering, and agentic frameworks (LangGraph, LangMem)
Hands-on experience with Azure OpenAI GPT-4/5, embedding models, and Azure cloud services
Strong background in Python, distributed systems, and enterprise architecture
Experience with Claude Code for agentic coding and AI-powered development
Proven track record in financial services or regulatory compliance environments
Expert knowledge of RAG architectures, advanced RAG patterns, and vector database optimization
Experience with Small Language Models (SLM), Agent-to-Agent (A2A) communication, and Model Context Protocol (MCP)
Proven ability to architect and scale AI solutions for enterprise workloads (1M+ documents, sub-second response times)
Key Responsibilities Design end-to-end AI solutions for private equity fund operations and financial automation
Architect scalable agentic AI frameworks using LangGraph, LangMem, and custom agent orchestration
Lead technical strategy for Azure OpenAI GPT-5 integration and advanced embedding-based retrieval systems
Design and implement advanced RAG architectures including hybrid search, query routing, and contextual retrieval
Establish multi-agent systems with Agent-to-Agent (A2A) communication protocols and Model Context Protocol (MCP)
Architect Small Language Model (SLM) integration for specialized tasks and cost optimization
Design enterprise-scale solutions supporting millions of documents with sub-second query response times
Establish AI governance, model safety protocols, and regulatory compliance frameworks
Lead architectural reviews for distributed AI systems, microservices, and cloud-native deployments
Hands-on development using Claude Code for rapid prototyping and agentic workflows
Drive architectural reviews for LlamaParse/Azure Document Intelligence integration
Design fault-tolerant, high-availability AI systems with automatic failover and load balancing
Establish comprehensive monitoring, observability, and performance optimization strategies
Mentor technical teams and establish AI engineering best practices using modern toolchains
Oversee model performance evaluation using LangGraph evals and DeepEval frameworks
TPBN1_UKTJ