New opportunity

Data Discovery and Enrichment Expert- Material Chemistry

RELX · India

About this role

Role Purpose: As a Data Discovery and Enrichment Expert, you will combine chemistry expertise with GenAI search practices to optimize how users find and retrieve chemistry information within the Reaxys platform. You will collaborate with Data Science and Technology partners to design, train, and validate new AI-driven search capabilities. Responsibilities: Support content enrichment through manual and AI-assisted automated extraction, focusing on materials chemistry. Provide subject-matter expertise on data elements and use cases for materials science industries such as polymers, batteries, catalysts, and semiconductors. Draft content extraction guidelines and data normalization approaches. Perform data analysis, create reports for content strategy, and conduct quality assurance on materials chemistry data. Requirements: PhD or post-doctoral experience in Materials Chemistry, Polymer Chemistry, or a closely related field with hands-on research experience. Strong understanding of materials science applications and the types of data valued by industry professionals. Ability to design evaluation datasets and assess content quality. Familiarity with how chemistry data is structured and retrieved in scientific information systems. Strong analytical and communication skills. Benefits: The company offers a comprehensive benefits package including health insurance for the employee and family, group life and accident insurance, flexible working arrangements, employee assistance programs, and various paid time off. Specific benefits for the Chennai location include subsidized meals and free transport.

For full details about this role, click “Apply on company site” to view the employer’s original posting.

Skills for this role

Generative AIMaterials ChemistryPolymer ChemistryData EnrichmentContent ExtractionData NormalizationData AnalysisQuality AssuranceScientific Information SystemsTaxonomies

Checking your profile…

Preparation suggestions, not the employer’s actual interview questions. Always check the original posting for current requirements.

Understand the role

What matters most

GenAI Search Optimization for Materials Chemistry
The core objective is to leverage deep chemistry expertise to train, validate, and refine AI-driven search capabilities within the Reaxys platform. You must translate complex materials science data needs into effective search behaviors that improve information retrieval for researchers.
Content Enrichment and Data Normalization
You are responsible for defining the standards for content extraction, both manual and AI-assisted. This requires drafting clear guidelines and normalization approaches that ensure materials science data—such as that for polymers, catalysts, and semiconductors—is structured consistently for scientific information systems.
Cross-Functional Collaboration with Technical Teams
Success depends on your ability to bridge the gap between scientific domain knowledge and technical implementation. You will work closely with Data Science and Technology partners to design evaluation datasets and ensure the AI models accurately interpret and represent materials chemistry data.

Likely challenges to think through

Bridging Domain Expertise with AI Logic
A significant challenge is communicating the nuances of materials chemistry to technical teams who may not share your scientific background. Prepare by practicing how to explain complex chemical data structures and research use cases in a way that informs AI training and validation processes.
Defining Quality in Automated Extraction
Designing evaluation datasets for AI-assisted extraction is difficult because scientific data is often unstructured or highly specialized. Prepare by reviewing methodologies for creating 'gold standard' test sets and defining metrics for accuracy and relevance in a scientific information retrieval context.

Practice your answers

Technical practice

Designing Evaluation Datasets for GenAI

What to coverExplain your methodology for creating high-quality test sets to validate AI-driven search capabilities. Focus on how you ensure the data covers diverse materials science use cases and how you measure the accuracy of automated content extraction.

Data Normalization in Materials Science

What to coverDescribe your approach to normalizing complex materials chemistry data, such as polymer properties or semiconductor specifications. Discuss the importance of maintaining consistency across different data sources and how you would draft guidelines for this process.

Integrating Chemistry Expertise with GenAI

What to coverHow do you bridge the gap between domain-specific chemistry knowledge and the technical requirements of training GenAI models? Provide examples of how you would translate scientific data needs into actionable instructions for data science and technology partners.

Quality Assurance for Scientific Data

What to coverWhat specific metrics or processes do you use to perform quality assurance on extracted materials chemistry data? Address how you handle ambiguity in scientific literature and ensure the data remains reliable for industry professionals.

Structuring Unstructured Scientific Information

What to coverDiscuss your experience with scientific information systems, taxonomies, or databases. Explain how you would approach transforming unstructured research findings into structured, searchable data elements.

Materials Chemistry Domain Knowledge

What to coverHow do you identify the specific data elements that are most valuable to researchers in fields like battery technology or catalysis? Suggestion: Prepare to discuss the types of parameters (e.g., thermal, mechanical, or electrical properties) that are critical for these industries.

AI-Assisted Content Extraction

What to coverCompare the challenges of manual versus AI-assisted automated content extraction in a scientific context. Discuss how you would validate the output of automated systems to ensure scientific accuracy.

Data Analysis for Content Strategy

What to coverHow do you use data analysis to inform content strategy and prioritization? Describe how you would report findings to stakeholders to justify focusing on specific materials science domains.

Behavioural practice

Cross-Functional Collaboration

What to coverDescribe a situation where you had to collaborate with technical partners (such as data scientists or engineers) to solve a complex problem. Focus on how you communicated your scientific expertise to ensure the technical solution met the domain requirements.

Managing Conflicting Priorities

What to coverGive an example of a time you had to prioritize different data extraction tasks or research projects. Explain how you balanced the needs of different stakeholders or industry use cases.

Handling Ambiguity in Research

What to coverDescribe a time when you encountered conflicting or ambiguous data in your research. How did you determine the correct interpretation, and what steps did you take to ensure the final result was accurate?

Adapting to New Technologies

What to coverTell me about a time you had to learn or apply a new technology (like GenAI or a new data platform) to your scientific work. What was the challenge, and how did you ensure your domain knowledge remained central to the implementation?

Sharpen your knowledge

Topics to prepare

Generative AI Search Architectures
Review how Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) systems function to retrieve scientific data. Exercise: Research the architecture of AI-driven search engines and how they handle domain-specific queries in chemistry to prepare for discussions on optimizing Reaxys search capabilities.
Materials Science Data Structures
Understand how complex materials data (polymers, semiconductors, catalysts) is represented in scientific databases. Exercise: Analyze existing open-access materials science datasets and taxonomies to identify common data elements and normalization challenges relevant to industry research.

Skills to revise

Evaluation Dataset Design
Develop the ability to create high-quality test sets for AI validation. Exercise: Draft a set of gold-standard queries and expected results for a specific materials chemistry topic, such as battery electrolyte performance, to demonstrate your approach to assessing AI search accuracy.
Content Extraction and Normalization
Practice defining guidelines for structured data extraction from unstructured scientific text. Exercise: Create a sample extraction template for a research paper abstract on polymer synthesis, focusing on defining clear rules for data normalization to ensure consistency across a database.
Quality Assurance for Scientific Data
Apply rigorous QA processes to technical content. Exercise: Perform a mock audit on a small set of scientific data entries, identifying potential errors in chemical nomenclature or property units and proposing a systematic correction workflow.

Your preparation checklist

Map Materials Science Data to Search Use Cases
Prepare a summary of how specific materials chemistry data—such as polymer properties, battery performance metrics, or semiconductor characteristics—are structured in scientific databases. Be ready to explain how this data is retrieved by researchers and where current search systems may fail to capture complex material relationships.
Develop a Framework for Evaluation Datasets
Draft a methodology for creating 'gold standard' test sets used to validate AI-driven search results. Define the criteria you would use to assess the accuracy, relevance, and quality of content extracted from scientific literature, specifically for materials science applications.
Prepare Examples of Content Extraction Guidelines
Create a sample set of guidelines for normalizing unstructured chemistry data. Show how you would instruct an AI or a human annotator to consistently extract key parameters from research papers, ensuring the output is standardized for a scientific information system.
Formulate Questions on AI-Human Collaboration
Prepare thoughtful questions for the interviewers regarding the current workflow between domain experts and data science teams at RELX. Focus on how they balance manual subject-matter expertise with automated GenAI extraction and how they prioritize content strategy for emerging materials fields.

Availability last checked: 18 Oct 2026. Status can change after a check; confirm on the employer’s website. Report an issue · Our checking policy

KEEP EXPLORING

Similar AI jobs

Related skills and specializations in India. Matched to this role, not your profile.

Explore more jobs

Finding similar opportunities…