Patsnap's Materials team builds AI systems that help R&D scientists and engineers search, extract, and reason over materials science and patent data. You will own the agentic layer of our products end-to-end: LLM-powered agents, tools (MCPs), and the evaluation frameworks that prove they beat general-purpose AI for our customers.
You will be the AI engineer for this team — sole owner of the agentic stack, working directly with product managers, materials domain experts, and our platform team.
What you will do
- Design, build, and productionize agentic systems (multi-step reasoning, tool orchestration, guardrails) for materials science search, Q&A and information extraction.
- Develop, integrate and maintain memory systems, MCP servers and agent skills in a multi-agent environment.
- Build evaluation frameworks with domain experts to measure answer quality, extraction accuracy, and retrieval performance.
- Own production reliability & observability of agents you develop.
- Advise adjacent teams on agentic and search system design; flag technical risk and feasibility during roadmap planning.
Requirements
- Degree in engineering, computer science, or a quantitative/physical science — or equivalent practical experience.
- 5+ years of software/ML engineering, including 2+ years building LLM-based systems that run in production.
- You have designed evaluations for LLM/agent systems — eval sets, quality metrics, human-expert or LLM-judge pipelines — and can walk us through one (e.g., promptfoo, Braintrust, LangSmith, DeepEval, or your own harness).
- You have instrumented, monitored, and debugged live AI services (e.g., OpenTelemetry, Arize Phoenix, Langfuse, Datadog, or similar).
- Strong Python; able to independently build and deploy services.
Strong pluses (not required — you'll have room and support to pick these up on the job)
- Search/RAG: vector databases, keyword search, knowledge graphs, reranking, hybrid retrieval
- MCP (Model Context Protocol) or agent-tool ecosystem experience
- Materials science, chemistry, or patent/IP domain exposure
- Structured information extraction from technical documents (tables, compositions, specs)
Why this role
- Full ownership of a production agent stack that customers pay for
- Your evals help decide the roadmap: we build where we can measurably beat frontier general agents
- Small senior team, direct access to domain experts and real R&D users
Skills Required
- Degree in engineering, computer science, or a quantitative/physical science (or equivalent experience)
- 5+ years software/ML engineering experience, including 2+ years building production LLM-based systems
- Designed evaluations for LLM/agent systems (eval sets, metrics, human-expert or LLM-judge pipelines)
- Instrumented, monitored, and debugged live AI services (e.g., OpenTelemetry, Arize Phoenix, Langfuse, Datadog)
- Strong Python; able to independently build and deploy services
- Search/RAG: vector databases, reranking, hybrid retrieval, knowledge graphs
- MCP or agent-tool ecosystem experience
- Materials science, chemistry, or patent/IP domain exposure
- Structured information extraction from technical documents (tables, compositions, specs)
What We Do
Founded in 2007, Patsnap is the company behind the world’s leading innovation intelligence platform. Patsnap is used by more than 10,000 customers in over 50 countries around the world to access market, technology, and competitive intelligence as well as patent insights needed to take products from ideation to commercialization. Customers are innovators across multiple industry sectors, including agriculture and chemicals, consumer goods, food and beverage, life sciences, automotive, oil and gas, professional services, aviation and aerospace, and education. To learn more about how Patsnap is improving the way companies innovate, visit www.patsnap.com.
.png)
