AI Harness Engineer

Charterhouse Partnership; Singapore; On-site; SGD 150,000 - 270,000; Full time

Job summary

Charterhouse Partnership in Singapore seeks a senior AI Harness Engineer to design scalable AI models and agent-based systems. You will shape frameworks for orchestration, context management, memory, and tool integration, while ensuring production-grade security and governance.

You will work across AI, technology, data and security teams to implement robust APIs, SDKs, and integration services, driving observability and reliability in a cloud-native production environment.

Qualifications

• 8+ years of experience in Software/AI engineering roles in relevant domains.
• Strong hands-on Python and fundamentals of software engineering.
• Experience designing production-grade applications with LLMs, RAG, or AI agents.
• Deep understanding of agent orchestration, context engineering, memory, and tool calling.

Responsibilities

• Design scalable, secure engineering frameworks for AI models and agent systems.
• Build capabilities for agent orchestration, context management, memory and tool integration.
• Develop evaluation, testing, and monitoring frameworks to improve AI quality and reliability.
• Implement security controls, guardrails, and governance for production AI apps.
• Build and maintain APIs, SDKs, libraries, and integration services.
• Establish best practices for observability, automated testing, and CI improvements.
• Integrate AI agents with enterprise data, APIs, workflows and ops systems.
• Contribute to cloud-native architecture and distributed production AI infra.
• Collaborate with AI, tech, data and security teams to translate requirements into scalable solutions.
• Provide technical guidance on architecture and engineering standards across teams.

Skills

Python

Software engineering

AI/ML engineering

Distributed systems

LLMs / RAG

API design

Security & governance

Cloud-native

Tools

LangGraph

LangChain

Job description

We’re looking for an AI Harness Engineer to join a leading organisation in Singapore.

Responsibilities:

• Design and develop scalable, secure, and reusable engineering frameworks for AI models and agent-based systems
• Build and enhance capabilities for agent orchestration, context management, memory, and tool integration
• Develop evaluation, testing, and monitoring frameworks to improve AI system quality, reliability, and performance
• Implement security controls, guardrails, and governance mechanisms for production AI applications
• Build and maintain APIs, SDKs, reusable libraries, and integration services
• Establish best practices for AI observability, automated testing, and continuous improvement
• Integrate AI agents with enterprise data, APIs, workflows, and operational systems
• Contribute to cloud-native architecture, distributed systems, and production AI infrastructure
• Work closely with AI, technology, data, and security teams to translate requirements into scalable technical solutions
• Provide technical guidance on architecture, engineering standards, and best practices across teams

Qualifications:

• 8+ years of relevant experience in Software Engineering, AI/ML Engineering, Platform Engineering, Distributed Systems, or related areas
• Strong hands-on experience with Python and software engineering fundamentals
• Experience designing and developing production-grade applications involving LLMs, RAG, or AI agents
• Strong understanding of agent orchestration, context engineering, retrieval, memory, and tool/function calling
• Experience with AI evaluation, observability, automated testing, or reliability engineering
• Strong knowledge of APIs, distributed systems, microservices, and system design
• Understanding of enterprise security principles, including authentication, authorisation, access controls, and secrets management
• Experience with cloud-native technologies and distributed computing environments
• Familiarity with AI frameworks such as LangGraph, LangChain, or similar technologies is a plus