AI Engineer – Autonomous Agent Development

About the role

We are looking for an AI Engineer to design and deliver autonomous AI agents that can reason, plan, and execute goal‑driven actions with minimal human oversight. You will work at the intersection of large language models, retrieval‑augmented generation, and enterprise integration to create intelligent, context‑aware systems.

Key responsibilities

• Design and implement autonomous AI agents capable of multi‑step reasoning, tool use, and structured decision‑making.
• Develop prompt‑engineering strategies, including chain‑of‑thought, role‑based prompting, and instruction design.
• Build memory architectures (short‑term and long‑term) to enable context‑aware interactions.
• Create evaluation frameworks to measure agent performance, accuracy, and reliability.
• Construct RAG pipelines that connect agents to organisational knowledge bases and document repositories.
• Integrate agents with internal APIs, data sources, and enterprise systems, and optimise vector‑search strategies using embedding models and vector databases.
• Design multi‑agent orchestration patterns (sequential, parallel, hierarchical) and routing logic for complex task execution.
• Leverage managed agentic services such as AWS Bedrock AgentCore and Microsoft Foundry Agent Service, and recommend hybrid architectures.
• Implement safety guardrails, human‑in‑the‑loop approvals, and observability pipelines for monitoring agent decisions.
• Collaborate with research units and corporate services to identify automation opportunities and provide technical guidance.

Required profile

• Proven experience in building AI agents or LLM‑based applications.
• Strong understanding of prompt engineering, retrieval‑augmented generation, and vector search technologies.
• Hands‑on experience integrating AI solutions with APIs and enterprise data sources.
• Familiarity with AI safety, governance, and data‑protection regulations (e.g., GDPR).
• Ability to prototype, evaluate, and iterate on complex AI workflows.

Required skills

• LLM reasoning and prompt engineering (chain‑of‑thought, role‑based prompting)
• Vector databases and embedding models for similarity search
• AWS Bedrock AgentCore
• Microsoft Foundry Agent Service
• Retrieval‑augmented generation (RAG) pipelines
• API integration and enterprise system connectivity
• GDPR and data‑protection compliance