AI Engineer - Materials

About the role

Patsnap's Materials team builds intelligent systems that help materials scientists and engineers search, extract and reason over materials science and patent data. You will own the agentic layer of the products end-to-end, from product development through to observability tooling and feedback loops in production. This is an in-office position in the Singapore office.

Key responsibilities

• Design, build and productionise agentic systems that outperform general-purpose AI agents in the domain.
• Develop MCP servers (tool design, description and schema) that improve the performance of other agents on domain tasks.
• Build evaluation frameworks with domain experts to measure answer quality, retrieval performance and scientific accuracy.
• Own production reliability and observability of the agents you develop, from instrumentation to model and provider evaluations.

Required profile

• Bachelor's degree in engineering, computer science or another field where analytical and critical thinking was demonstrated.
• 5+ years of software or ML engineering, including 1+ year building and maintaining production LLM-based systems.
• Experience designing evaluations for LLM or agent systems, such as eval sets, quality metrics and human-expert or LLM-judge pipelines.
• Experience instrumenting, monitoring and debugging live AI services.
• Nice to have: API/SDK or MCP server design experience, and exposure to materials science, chemistry or patent/IP domains.

Required skills

• Strong software engineering and system design fundamentals.
• Experience with tools such as OpenTelemetry, Arize Phoenix, Langfuse or Datadog.