Senior AI Engineer - Agentic AI

In this role you will design and build scalable agentic AI platforms that integrate LLMs, multi-agent orchestration and RAG into enterprise solutions. You’ll create reusable platform components, orchestration engines and governance frameworks to run complex AI workflows securely at scale. You’ll implement evaluation and observability tooling and enterprise controls for compliance and safety. This is an opportunity to drive production-grade AI engineering and impact real-world applications with scalable intelligent systems.

• ESPP
• life assurance and income protection
• private medical insurance
• pension plan
• cycle scheme and transport loans
• learning and development opportunities

• Design, build and deploy Generative AI and Agentic AI solutions from prototype to production
• Implement multi-agent orchestration patterns using LangGraph, CrewAI, AutoGen, Semantic Kernel or OpenAI Agents SDK
• Develop orchestration backbone for workflows including planning, checkpointing, retries, fallback handling and resumption of long-running processes
• Build and optimize RAG pipelines with chunking, embeddings, vector/hybrid search and grounded, cited responses
• Develop memory and context management solutions (short-term and long-term stores, compaction)
• Write robust Python APIs and services (e.g., FastAPI) with async execution, background jobs and containerized deployments
• Integrate enterprise systems using MCP, A2A, OpenAPI, REST and gRPC with graceful degradation and retries
• Apply enterprise security and governance practices including RBAC, prompt safety, traceability and secrets management
• Implement evaluation pipelines and observability frameworks using Langfuse, Arize or OpenTelemetry
• Contribute to architectural decisions, code reviews and engineering standards

• Bachelor’s or Master’s degree in Computer Science, Engineering or related field (PhD is a plus)
• Practical experience delivering Generative AI or Agentic AI systems into production
• Expertise in Python for APIs, microservices, testing and CI/CD
• Strong knowledge of LLM capabilities including prompt design and retrieval strategies
• Hands-on experience with agent orchestration frameworks (LangGraph, AutoGen, CrewAI or Semantic Kernel)
• Proven experience with RAG implementations, embeddings and vector database integrations
• Familiarity with stateful/long-running systems including checkpointing and resumable workflows
• Cloud deployment experience (Azure preferred) using Azure OpenAI, AI Foundry or AI Search, with Docker and Kubernetes
• Understanding of schema validation frameworks (JSON Schema, Pydantic) and MLOps tools such as MLflow or Airflow
• Strong communication to explain trade-offs around cost, latency and accuracy

• strong communication
• problem-solving
• ability to explain trade-offs to technical and non-technical audiences
• Python
• APIs and microservices
• FastAPI