Application Architect

<p>Application Architect L1 (AI/ML & Agentic AI Platforms)</p><p><strong>Skill Group:</strong> GCP AI/ML – Vertex AI</p><p><strong>Location:</strong> Manchester, UK (2 Days Onsite)</p><p><strong>Employment Type:</strong> Long-Term Contract</p><p><br><br>Please ensure you read the below overview and requirements for this employment opportunity completely.<br></p><p>Role Overview</p><p>We are seeking an experienced <strong>Application Architect L1</strong> with strong expertise in <strong>Google Cloud AI/ML technologies</strong>, <strong>Agentic AI systems</strong>, and modern cloud-native architecture. The ideal candidate will design and deliver scalable AI-powered enterprise solutions using <strong>Google Gemini on Vertex AI</strong>, orchestration frameworks, and knowledge-driven architectures.</p><p>This role requires deep technical proficiency in <strong>Python</strong>, <strong>Google Cloud Platform (GCP)</strong>, containerized deployments, and semantic data modeling, along with experience building intelligent systems powered by LLMs, RAG pipelines, and autonomous agents.</p><p>The position is based in <strong>Manchester, UK</strong>, with a hybrid working model requiring <strong>2 days onsite per week</strong>.</p><p><br></p><p>Key Responsibilities</p><ul><li>Design and architect enterprise-grade AI/ML solutions on <strong>Google Cloud Platform (GCP)</strong>.</li><li>Develop AI applications using <strong>Google Gemini models via Vertex AI</strong>.</li><li>Build intelligent agent workflows using <strong>Google Agent Development Kit (ADK)</strong>.</li><li>Architect and deploy scalable microservices using <strong>Python</strong> and <strong>FastAPI</strong>.</li><li>Implement cloud-native deployments using <strong>Docker</strong> and <strong>Google Kubernetes Engine (GKE)</strong>.</li><li>Design and manage <strong>Knowledge Graphs</strong>, RDF/property graph structures, and semantic models.</li><li>Build Retrieval-Augmented Generation (RAG) pipelines integrating enterprise knowledge sources and vector search.</li><li>Collaborate with engineering, product, and business teams to define scalable AI architectures.</li><li>Optimize application performance, scalability, security, and reliability.</li><li>Evaluate and improve LLM outputs using frameworks such as <strong>ARES</strong>, <strong>Ragas</strong>, and <strong>DeepEval</strong>.</li><li>Provide architectural guidance, technical leadership, and best practices to development teams.</li></ul><p><br></p><p>Required Skills</p><ul><li>Strong hands-on experience with:</li><li><strong>Google Gemini (Vertex AI)</strong></li><li><strong>Google Agent Development Kit (ADK)</strong></li><li><strong>Python</strong></li><li><strong>Google Cloud Platform (GCP)</strong></li><li><strong>Google Kubernetes Engine (GKE)</strong></li><li><strong>Docker</strong></li><li><strong>Knowledge Graphs</strong></li><li><strong>RDF / Property Graphs</strong></li><li><strong>Semantic Modelling</strong></li><li>Experience designing scalable cloud-native and distributed systems.</li><li>Strong understanding of AI/ML solution architecture and LLM integration patterns.</li><li>Experience with API-driven and microservices-based architectures. xwzovoh </li><li>Excellent communication and stakeholder management skills.</li></ul>