Senior AI Engineer: Agentic Systems for AI Factories

Firmus; Singapore; On-site; SGD 120,000 - 180,000; Full time

Job summary

Firmus Technologies is seeking a Senior AI Engineer (Agents & Applications) to design, build, and operate production-grade agentic systems coordinating the AI‑factory lifecycle. You will integrate models, inference endpoints, and scheduling with safety, observability, and human approvals as core requirements.

The role emphasizes architecting multi-agent workflows, retrieval-augmented pipelines, and end-to-end operational orchestration within Firmus AI Cloud.

Qualifications

• 5+ years of software engineering experience, including 3+ years building AI/ML applications, distributed systems, automation platforms, data products, or production workflow systems.
• Experience delivering LLM-powered, agentic, retrieval-augmented, decision-support, or operational-automation applications into production.
• Strong Python expertise, including experience with FastAPI or comparable API frameworks, asynchronous programming, event-driven services, distributed task execution, data pipelines, and API integrations.
• Hands-on experience with one or more agent frameworks, such as LangGraph, LangChain, LlamaIndex, Microsoft AutoGen, Semantic Kernel, CrewAI, PydanticAI, Haystack, DSPy, or equivalent in-house agent framework.
• Demonstrated ability to build custom agent orchestration when frameworks are insufficient, including state machines, graph-based execution, durable workflow execution, task queues, tool routers, model routers, planners, evaluators, and human-approval flows.

Responsibilities

• Design, build, and operate agentic applications supporting AI-factory planning, commissioning, validation, workload onboarding, benchmark analysis, model and recipe optimisation, scheduling, operations, maintenance, incident response, and continuous improvement.
• Define reference architectures for single-agent, multi-agent, workflow-based, event-driven, and human-in-the-loop agentic systems.
• Build orchestration workflows using appropriate agent frameworks and libraries, such as LangGraph, LangChain, LlamaIndex, Microsoft AutoGen, Semantic Kernel, CrewAI, PydanticAI, Haystack, DSPy, or equivalent custom-built frameworks.
• Select the appropriate architecture for each use case rather than applying multi-agent patterns by default.
• Develop the intelligent coordination layer for Model-to-Grid, enabling agents to reason across model characteristics, inference and training configuration, validated recipes, GPU resources, topology, scheduling policies, and operational constraints.
• Build Retrieval-Augmented Generation (RAG) pipelines using vector retrieval, hybrid search, metadata filtering, reranking, and knowledge graphs.

Skills

Python

AI/ML applications

Distributed systems

Agent frameworks

Tools

LangGraph

LangChain

LlamaIndex

Microsoft AutoGen

Semantic Kernel

CrewAI

PydanticAI

Haystack

DSPy

Job description

Firmus Technologies is seeking a Senior AI Engineer (Agents & Applications) to design, build, and operate production-grade agentic systems coordinating the AI‑factory lifecycle. You will integrate models, inference endpoints, and scheduling with safety, observability, and human approvals as core requirements.

The role emphasizes architecting multi-agent workflows, retrieval-augmented pipelines, and end-to-end operational orchestration within Firmus AI Cloud.