Founding Engineer, AI Agents

MIAO WORLDS PTE. LTD.; Singapore; On-site; SGD 180,000 - 280,000; Full time

Job summary

MiAO AI in Singapore is seeking an experienced engineer to architect the agent system that bridges intelligence and product reliability. You will design the runtime, memory, and security layers, turning emergent model capabilities into deterministic, reliable user experiences.

You will join a small core team, reporting to the founders, collaborating with Product and Software Engineers. You will define standards for observability, evaluation, and cross-language integration, while shaping the

Qualifications

• 5+ years of software engineering experience in production environments.
• Experience designing production-grade agent systems or complex distributed systems.
• Deep understanding of how LLM capabilities shape agent architecture.
• Strong knowledge of context engineering and cross-language integration.

Responsibilities

• Design and build the core agent runtime architecture and ensure reliable execution.
• Define memory and context management strategies for agents across sessions.
• Develop security boundaries for autonomous agents operating in sandboxes.
• Architect multi-agent orchestration, task decomposition, and result aggregation.
• Define observability and evaluation standards to measure and improve reliability.
• Set technical standards and contribute to product strategy and technical roadmap.

Skills

Agent systems

Distributed systems

LLM integration

Context engineering

TypeScript

Python

Job description

About MiAO AI

MiAO AI was founded in 2025 and is headquartered in Singapore, having raised over SGD 95 million from globally renowned investors. Our founding team previously built large-scale live-service gaming products with over 25 million DAU and 100 million MAU.

Our mission: Let AI discover you.

The next leap in AI isn't about getting smarter - it's about becoming yours. Seventy years of AI research keep proving the same thing: general methods win over clever designs. Models are getting stronger. Protocols are converging. Infrastructure is commoditizing. But one layer remains scarce - the layer that makes AI truly yours.

We're building personal AI agents - an AI that knows you better on day 30 than day 1, not because it got stronger, but because you shaped it.

Our workflow is 100% AI-driven - engineering, product, operations, no exceptions. No middle management. Radically flat. Every team member gets unlimited access to frontier AI models. We spend on efficiency, not process.

Who we're looking for: Believe in the Bitter Lesson - let AI discover, not discover for it.

About This Role

You are the architect between model intelligence and product reliability. You design the entire agent system architecture - from runtime to orchestration, from context engineering to security boundaries - turning emergent model capabilities into deterministic, reliable product experiences. You build the technical foundation the team develops on, and set engineering standards.

You’ll join a small, elite core team, reporting directly to the founders, working closely with Product Engineers and Software Engineers.

What You'll Do

• Design and build the core agent runtime architecture - how agents think, execute, verify, and recover from errors
• Design the agent's memory and context architecture - enabling AI to make optimal decisions within limited attention and accumulate understanding of users across sessions
• Build the agent security layer - enabling highly autonomous agents to run safely in sandboxes while protecting user data privacy
• Design multi-agent orchestration - task decomposition, concurrent execution, and result aggregation
• Design the architecture and standards for observability and evaluation systems - defining how to measure and improve agent reliability
• Set technical standards, contribute to product strategy and technical roadmap

You May Be a Good Fit If You...

• Your daily workflow is 100% AI-driven - AI isn't an assistive tool, it's your default way of working
• 5+ years of software engineering experience, having designed and delivered production-grade agent systems or complex distributed systems - not prototypes, but real products serving real users
• Deep understanding of how LLM capabilities shape agent architecture - able to articulate the tradeoffs between different execution strategies
• Deep understanding of context engineering - knowing how to help agents make optimal decisions within limited context
• Able to build efficiently across multiple languages - from web applications to sandboxed execution environments (e.g., TypeScript, Python, Bash)
• Verification-first design instinct - believing that designing "how to verify" is harder than designing "how to execute"

Nice to Have

• Production experience with agent self-evolution, multi-agent orchestration, or MCP server design
• Technical community influence (open source contributions, technical writing, or conference talks)