Formulation Domain Specialist (Knowledge Architect)
Patsnap’s Materials team is building structured formulation knowledge from patents, scientific literature, and technical sources to support our Formulation Agent. The agent helps scientists turn product targets, existing formulas, required claims, and ingredient constraints into evidence-backed formulation directions, including ingredient roles, concentration ranges, processing considerations, and supporting references.
You will define how this knowledge is represented and evaluated: how ingredients, quantities, processes, tested samples, properties, and claims are connected, and what the underlying evidence supports. Working with formulation scientists, data scientists, engineers, and product managers, you will translate expert judgment into schemas, curation guidelines, benchmarks, and evaluation rules that improve the quality and traceability of our formulation products.
This position is based in our Singapore office.
Want to see the platform you'd be representing?
Check out this short overview:
This is an in-office position based in our Singapore office.
Who are we?
Founded in Singapore, Patsnap is a global, pre-IPO company serving more than 18,000 organizations worldwide. We combine patent, scientific, chemical, materials, and life sciences data with domain-specific AI products to help IP and R&D teams make better decisions across the innovation lifecycle.
Our international team works across Singapore, Toronto, London, Shanghai, and the United States, turning complex scientific and technical knowledge into products used by R&D teams around the world.
What You’ll Be Doing
Define and maintain the knowledge model for formulations, including ingredients, functions, concentrations, processes, properties, test methods, and performance results.
Establish evidence and quality standards, including how proposed, prepared, and tested formulations are distinguished and how provenance, confidence, and conflicting information are represented.
Develop normalization rules that connect formulation information across patents, scientific literature, datasheets, and other technical sources.
Build guidelines, benchmarks, and evaluation datasets for formulation extraction, search, and AI-generated outputs.
Work with product, data science, and engineering teams to turn expert judgment and user feedback into improvements to the data and product.
Lead the review and resolution of complex formulation-data questions and support the quality management of internal or external curation work.
Why This Role
Help AI understand formulation information with greater scientific accuracy and traceability.
Turn formulation expertise into structured rules and standards that can be applied across large volumes of technical content.
Directly influence the quality of Patsnap’s formulation data and AI products used by R&D teams.
Core Requirements
Degree in formulation science, chemistry, polymer science, materials science, chemical engineering, pharmaceutical science, cosmetic science, or a related field.
At least 5 years of relevant experience in formulation R&D, scientific information analysis, technical data curation, or knowledge management.
Strong understanding of formulation design, including ingredient functions, concentrations, processing conditions, test methods, and performance relationships.
Ability to evaluate evidence across patents, scientific papers, technical datasheets, and experimental records.
Experience developing structured domain knowledge through schemas, taxonomies, controlled vocabularies, normalization rules, or similar approaches.
Ability to translate scientific judgment into clear, repeatable guidelines and quality standards.
Strong project leadership and cross-functional communication skills. Professional working proficiency in English and Chinese is required.
Nice to Have
Hands-on experience developing or troubleshooting formulations in cosmetics, chemicals, coatings, polymers, pharmaceuticals, or related industries.
Experience with formulation informatics, experimental data management, design of experiments, ELN, or LIMS systems.
Experience with knowledge graphs, entity resolution, chemical structure data, information retrieval, or search evaluation.
Familiarity with how LLM-based products retrieve, evaluate, and use scientific knowledge.
Experience with patent analysis, prior-art search, novelty assessment, or freedom-to-operate analysis.