Agent Harness Engineer (Agent Runtime & Infrastructure) | AI Agent Company

DADACONSULTANTS PTE. LTD.; Singapore; On-site; SGD 120,000 - 200,000; Full time

Job summary

DADACONSULTANTS PTE. LTD. in Singapore seeks a senior software engineer to build the core systems of the AI agent runtime and control layer, owning context, memory, model and tool orchestration, planning and execution.

You will drive design, rollout and ongoing improvements, enhance agent performance through context engineering, prompting, retrieval and architecture, and collaborate with product, research, infra and security to identify risks and ensure reliable delivery.

Qualifications

• 5+ years of software engineering experience with shipping production systems.
• Strong backend or distributed-systems foundations: concurrency, queues, persistence, observability.
• Ability to independently own complex systems or critical components and ensure delivery quality.
• Effective use of AI tools for research, coding and validation, while using your own judgement.

Responsibilities

• Own core components across context and memory, model and tool orchestration, task planning and execution.
• Define the problem and success criteria when requirements and approaches are unclear, then drive design, implementation, rollout and ongoing improvement.
• Improve agent performance through context engineering, prompt design, retrieval, tooling and architecture.
• Build reproducible agent evaluations, regression tests and end-to-end observability, using real tasks and production failures to guide improvements.
• Work with product, research, infrastructure and security teams on design reviews and risk identification.

Skills

5+ years exp

Distributed systems

Ownership

AI tooling

Job description

About our client

Our client is a fast-growing, well-funded AI agent company. The product takes on complex work like deep research, data analysis and software development, and carries it through to a finished result. It is a small team building at the frontier, based in Singapore.

About the role

You will build the core systems of the agent runtime and control layer: context, tools, execution, feedback and safety boundaries. You'll own the design and delivery of complex components, and make the agent more reliable on real-world tasks.

What you'll do

• Own core components across context and memory, model and tool orchestration, task planning and execution, tool and MCP integrations, and evaluation and quality feedback
• Define the problem and success criteria when requirements and approaches are unclear, then drive design, implementation, rollout and ongoing improvement
• Improve agent performance through context engineering, prompt design, retrieval, tooling and architecture, measured on task success, reliability, latency and cost
• Build reproducible agent evaluations, regression tests and end-to-end observability, using real tasks and production failures to guide improvements
• Work with product, research, infrastructure and security teams on design reviews and risk identification

What you bring

• 5+ years of software engineering experience (or equivalent ability), with a record of shipping maintainable, testable production systems
• Strong backend or distributed-systems foundations: concurrency, task queues, persistence, idempotency, failure recovery and observability
• Ability to independently own complex systems or critical components, and take responsibility for delivery quality
• Effective use of AI tools for research, coding and validation, while keeping your own judgement

Nice to have

• Production experience with agent runtimes, multi-step workflows, task scheduling, browser automation, CI runners or code-execution systems
• Deep experience in context engineering, long-term memory, retrieval and ranking, model routing, tool use, MCP, multi-agent systems or agent evaluation
• Experience with execution isolation, least privilege, multi-tenancy, prompt-injection defence or auditing
• Open-source work or technical writing

What we offer

• Build at the frontier of AI agents with a fast-paced team
• Unlimited access to own AI tools