Senior Agent Researcher — AI Systems & Multi-Agent Innovation

Search Staffing Pte Ltd; Singapore; On-site; SGD 120,000 - 180,000; Full time

Job summary

Our Singapore-based client in automotive AI is seeking a Senior Agent Researcher / Engineer to design and build evaluation-driven Agent and multi-agent systems. You will focus on understanding, measuring, and improving agent behavior within an AI-native development environment.

The role requires hands-on experience with agent evaluation, AB testing, and translating cutting-edge research (LLMs, multi-agent systems) into production-ready solutions, balancing engineering execution with research

Qualifications

• Experience designing, building or deploying Agent systems, LLM-based applications, or AI systems in production.
• Strong understanding of AI/ML fundamentals, system design, including models, inference, training, context, and evaluation.
• Hands-on experience with Agent evaluation frameworks, automated experimentation, or A/B testing.
• Ability to translate research (LLMs, MLLMs, multi-agent systems) into production-ready solutions.
• Strong systems thinking with a research-oriented mindset and solid engineering execution.

Responsibilities

• Build and evolve evaluation-driven Agent systems with evaluation as the core for behavior improvement.
• Design Agent architectures that are observable, maintainable, and optimizable in real-world constraints.
• Develop scalable evaluation infrastructure including automated testing, benchmarking, and experiments.
• Optimize Agent performance across architecture, model selection, context management, memory, and tool usage.
• Prototype Agent systems and demos, integrating research insights with engineering and product validation.
• Explore and apply advancements in LLMs, multimodal models, multi-agent systems and context engineering.

Job description

Our Singapore-based client in automotive AI is seeking a Senior Agent Researcher / Engineer to design and build evaluation-driven Agent and multi-agent systems. You will focus on understanding, measuring, and improving agent behavior within an AI-native development environment.

The role requires hands-on experience with agent evaluation, AB testing, and translating cutting-edge research (LLMs, multi-agent systems) into production-ready solutions, balancing engineering execution with research