Sepenuh Masa AI Engineer Jobs, salary up to SGD 4,000 in V-ELEGANT PTE. LTD. - Maukerja

Responsibilities

• Design and build a reusable multi-agent AI system that can support multiple projects and use cases
• Define agent roles, responsibilities, and interaction patterns, including planning, coordination, and handoff
• Implement agent orchestration using frameworks such as: LangChain, LangGraph, CrewAI
• Integrate both self-hosted LLM models and commercial LLM services
• Develop backend services in Python, including:

1. Agent orchestration and execution logic
2. Tool integration and external API access
3. Backend APIs for frontend consumption

• Develop and maintain frontend components using React.js, including:

1. User interfaces for interacting with AI agents
2. Visualisation of agent outputs and intermediate results
3. Human-in-the-loop workflows such as review, approval, and override

• Implement agent evaluation and monitoring mechanisms, covering:

1. Response quality and correctness
2. Performance and latency
3. Cost and resource usage

• Work with business users from different departments to understand requirements and workflows, and translate business problems into agent-based solutions
• Produce technical documentation, including design documentation, agent patterns and usage guidelines

Requirements

• Strong hands-on experience with multi-agent AI system design and implementation
• Proficient in Python for backend development and React.js for frontend development
• Practical experience using LangChain, LangGraph, CrewAI, or similar agent frameworks
• Experience working with both self-hosted LLMs and commercial LLM APIs
• Familiarity with agent evaluation approaches and AI quality assessment
• Good understanding of LLM limitations, such as hallucinations and non-deterministic behaviour
• Ability to design reliable systems with appropriate guardrails and human-in-the-loop controls
• Strong communication skills and ability to engage business users with varying technical backgrounds
• Able to work independently while collaborating closely with internal teams