Backend Engineer (Multiple HC) - AI Agents / Information Technology / AI adoption / Internet / [...]
Summary
Build and scale enterprise-grade AI Agent systems, focusing on RAG, tool-calling, and multi-agent collaboration for intelligent automation workflows.
Our clients are fast growing technology companies building enterprise-grade AI Agents that power the next generation of intelligent automation. They are seeking a talented AI Agent Backend Engineer to join their core engineering team and take ownership of designing and scaling robust Agent systems. This is a high-impact role for someone who wants to shape the technical direction of an AI platform at the frontier of agentic AI development.
Key Responsibilities
- Develop end-to-end performance optimisation of enterprise-grade AI Agent systems, ensuring reliability and stability under high-concurrency production environments
- Implement and refine key modules including Retrieval-Augmented Generation (RAG), tool-calling interfaces, and multi-agent collaboration frameworks to support complex business workflows
- Package and standardise reusable AI components that accelerate product iteration cycles and improve engineering efficiency across teams
- Drive technical advancements in Agent context engineering, high-performance execution pipelines, and self-optimisation mechanisms
- Design and maintain benchmark Agents to evaluate system performance and validate new capabilities against real-world scenarios
- Proactively research and integrate emerging Agent technologies to maintain a competitive edge within the team's development platform
- Collaborate closely with cross-functional stakeholders to translate business requirements into scalable, production-ready Agent solutions
Requirements
- Bachelor's degree or above in Computer Science, Software Engineering, or a related discipline, with at least 1 years of hands-on software engineering experience in one or more of the following: Python, TypeScript, Java, Golang or C/C++
- Demonstrated experience contributing to enterprise-level Agentic AI projects, with solid working knowledge of Agent frameworks including Agent Harness and Agent Loop concepts
- In-depth familiarity with the design philosophy of at least one mainstream Agent or LLM orchestration framework (e.g., LangChain, Dify, or equivalent open-source tooling)
- Strong understanding of agentic AI principles including planning, memory management, tool use, and multi-agent coordination patterns
- Active participation in open-source AI or developer communities (is a bonus)