Kerja Sepenuh Masa, Software Engineer – AI Agent Platforms - Distributed Systems di Carro Central Region (Singapore) - Maukerja

Don’t just build AI features. Engineer the systems that make AI agents work at scale.

The next frontier of AI isn’t just about smarter models. It’s about building the infrastructure that enables AI agents to reason, execute multi-step tasks, use tools, manage context, recover from failures, and operate securely across complex enterprise environments.

We’re looking for a Software Engineer – AI Agent Platforms & Distributed Systems to help architect and build our next-generation enterprise AI agent orchestration platform.

If you’re passionate about distributed systems, asynchronous runtimes, real-time streaming, and production-grade LLM applications, this is your opportunity to work at the intersection of AI innovation and serious backend engineering.

What You’ll Build

Core AI Agent Engine & Orchestration

• Design and scale asynchronous, multi-tenant agent runtime engines.
• Build stateful task execution graphs, workflow orchestration, verification, and error recovery mechanisms.
• Engineer model gateway routing with provider failover, load balancing, and token-cost optimization.

️ Dynamic Tooling & Execution Frameworks

• Develop systems that enable AI agents to dynamically discover, generate, and execute typed tools.
• Build extensible tool registries, runtime code execution, and secure execution sandboxes.
• Explore metaprogramming, schema inference, and dynamic code generation to expand agent capabilities.

Real-Time Streaming & Enterprise Integrations

• Build resilient, high-throughput event pipelines using WebSockets and modern messaging technologies.
• Enable real-time agent interactions, progressive response streaming, and connection recovery.
• Integrate with enterprise collaboration tools, document platforms, spreadsheets, APIs, and databases.

Multi-Tenant Data, Memory & State

• Architect PostgreSQL-backed systems for tenant isolation, session state, and agent configuration.
• Design multi-tier memory architectures spanning global, session-scoped, and contextual state.
• Build reliable background processes for memory consolidation and state management.

Security, Reliability & Governance

• Implement execution sandboxing, secrets protection, SSRF defenses, and prompt-injection mitigations.
• Establish observability, structured logging, latency monitoring, and comprehensive audit trails.
• Engineer for enterprise-grade security, reliability, and scalability from the ground up.

You’ll be a strong fit if you have:

Strong backend engineering skills in TypeScript / Node.js or an equivalent modern backend stack.

Deep understanding of asynchronous programming, event-driven architectures, streaming, and distributed systems.

Hands-on experience building LLM-powered applications or production AI systems involving tool/function calling, agentic workflows, prompt management, and context/token optimization.

Experience with PostgreSQL, relational data modeling, schema validation (Zod / JSON Schema), and ORMs such as Drizzle, Prisma, or TypeORM.

Solid knowledge of REST APIs, WebSockets, real-time communication, and client-server state synchronization.

An appreciation for secure system design, authentication, credential management, and runtime isolation.

You’ll stand out even more if you have:

• Experience with LangChain, LangGraph, AutoGen, LlamaIndex, or custom agent frameworks.
• Built enterprise integrations, productivity bots, or collaboration platform extensions.
• Worked with AST parsing, metaprogramming, dynamic code generation, or sandboxed execution environments.
• A degree in Computer Science, Software Engineering, or equivalent practical experience.

Why Join Us?

• Build at the core of enterprise AI: Work on the orchestration infrastructure powering autonomous AI agents, not just the application layer.
• Own meaningful engineering challenges: Take responsibility for architecture, technical decisions, and production outcomes.
• Move fast, build boldly: Join a high-autonomy engineering environment with rapid deployment cycles.
• Shape the technical roadmap: Collaborate directly with engineering leadership to define platform architecture and engineering standards.