Role Purpose: As a Chemistry Content Expert for Agentic Solutions, you will bridge the gap between deep chemistry expertise and Generative AI search practices. You will work within a team that transforms scientific information into structured data, collaborating with Data Science and Technology partners to design, train, and validate AI-driven search capabilities for Reaxys. Responsibilities: Support the development and validation of chemistry connectors for agentic solutions. Create test sets and evaluation datasets to assess the quality, accuracy, and reliability of these connectors. Analyze connector outputs against expected results to identify gaps, errors, or edge cases. Perform data analysis and generate reports summarizing evaluation results and recommendations. Partner with cross-functional teams to communicate findings and support issue resolution. Requirements: PhD or post-doctoral experience in Organic Chemistry or a closely related field, with hands-on laboratory or research experience. Ability to design evaluation/test datasets and assess the quality of outputs from chemistry-related tools. Understanding of how chemistry data is structured, represented, and retrieved in scientific information systems. Strong analytical and communication skills. Familiarity with or interest in AI/NLP-based or agentic systems is considered a plus. Benefits: The company offers a comprehensive benefits package including health insurance for the employee and family, group life and accident insurance, flexible working arrangements, an employee assistance program, and various paid time off options. Additional perks include subsidized meals and free transport in Chennai.
For full details about this role, click “Apply on company site” to view the employer’s original posting.
Skills for this role
Organic ChemistryGenerative AIAI SearchData AnalysisEvaluation DatasetsNLPAgentic SystemsScientific Information Systems
Your skill match
Checking your profile…
YOUR NEXT STEP
Get interview-ready for this role
A focused preparation guide, built around this job’s responsibilities and requirements.
✦ AI-generated guide
Preparation suggestions, not the employer’s actual interview questions. Always check the original posting for current requirements.
01
Understand the role
What matters most
Evaluation Dataset Design
The core responsibility is creating high-quality test sets to validate chemistry connectors. You must demonstrate the ability to translate complex organic chemistry queries into structured evaluation frameworks that can reliably measure the accuracy and reliability of AI-driven search outputs.
Cross-Functional Collaboration
You will act as the bridge between deep chemistry domain knowledge and technical Data Science/Engineering teams. Success depends on your ability to communicate scientific findings clearly to non-chemists and work iteratively to resolve technical gaps in AI search performance.
Chemistry Data Structuring
You must apply your understanding of how chemical information is represented in scientific databases and taxonomies to ensure that AI agents correctly interpret and retrieve structured chemistry data, moving beyond simple keyword matching.
Likely challenges to think through
Bridging Domain Expertise and AI Logic
A primary challenge is reconciling the nuance of organic chemistry with the probabilistic nature of Generative AI. Prepare by being ready to discuss how you would handle 'hallucinations' or edge cases where AI might misinterpret chemical structures or reaction conditions.
Defining 'Ground Truth' for AI
In AI development, creating objective metrics for subjective search quality is difficult. You will likely face challenges in defining what constitutes a 'correct' answer for complex research queries; prepare by thinking about how to build robust rubrics that account for scientific accuracy and relevance.
03
Practice your answers
Technical practice
Designing Evaluation Datasets for Chemistry AI
What to coverExplain your methodology for creating high-quality test sets to validate AI-driven chemistry search. Discuss how you ensure the dataset covers diverse chemical structures, reaction types, and edge cases to rigorously test system reliability.
Structuring Chemical Information for Retrieval
What to coverDescribe your experience with how chemical data is represented in scientific information systems, such as databases or taxonomies. Discuss the challenges of mapping unstructured chemical literature into structured formats suitable for AI ingestion.
Analyzing AI Connector Outputs
What to coverHow do you systematically analyze the output of a chemistry-focused AI connector against ground truth? Detail your process for identifying, categorizing, and reporting on errors, hallucinations, or retrieval failures.
Bridging Chemistry Expertise and NLP
What to coverHow would you translate complex organic chemistry concepts into requirements for data scientists building agentic systems? Provide an example of how you ensure technical teams accurately interpret chemical domain nuances.
Evaluating Agentic Search Performance
What to coverWhat metrics would you prioritize when evaluating the performance of an AI agent designed to retrieve chemical data? Discuss the trade-offs between precision and recall in the context of scientific research tools.
Handling Chemical Edge Cases in AI
What to coverDescribe how you would approach testing for rare or complex chemical reactions that might not be well-represented in training data. How do you ensure the AI system maintains accuracy for non-standard queries?
Reporting and Communicating Findings
What to coverWhen summarizing evaluation results for cross-functional teams, what key information do you include to drive actionable improvements? Suggest how you balance technical depth with the need for clear recommendations for developers.
Behavioural practice
Cross-Functional Collaboration
What to coverDescribe a situation where you had to work with a technical team (e.g., developers or data scientists) to resolve a complex issue. How did you ensure your scientific expertise was effectively integrated into their technical workflow?
Managing Conflicting Priorities
What to coverTell me about a time you had to balance multiple evaluation tasks or project deadlines. How did you prioritize your work to ensure the quality of the output was not compromised?
Communicating Technical Insights
What to coverGive an example of a time you had to explain a complex scientific or data-related finding to a non-expert stakeholder. How did you adapt your communication style to ensure they understood the implications?
Problem-Solving in Research
What to coverDescribe a challenging research or laboratory problem you encountered. What steps did you take to analyze the root cause, and what was the final outcome of your intervention?
02
Sharpen your knowledge
Topics to prepare
Evaluation Frameworks for Generative AI
Study methodologies for assessing the accuracy, reliability, and hallucination rates of AI models. Exercise: Design a rubric to evaluate the output of a hypothetical chemistry search agent, focusing on identifying factual errors in chemical nomenclature or reaction conditions.
Scientific Information Retrieval Systems
Understand how chemistry data is structured in databases and taxonomies. Exercise: Research how chemical structures (e.g., SMILES, InChI) are indexed in scientific databases and how this impacts search precision and recall.
Skills to revise
Test Dataset Creation
Develop high-quality datasets for training and validating AI connectors. Exercise: Create a set of 20 diverse chemistry-related queries and their expected, ground-truth answers to test a search system's ability to retrieve accurate scientific data.
Data Analysis and Reporting
Analyze system output against expected results to identify edge cases. Exercise: Take a sample of AI-generated search results, compare them against a known scientific source, and draft a summary report highlighting specific failure modes or accuracy gaps.
04
Your preparation checklist
Develop a framework for evaluating AI-driven search
Create a sample evaluation plan that outlines how you would test the accuracy and reliability of an AI agent retrieving chemistry data. Define metrics for success, such as precision, recall, and relevance of search results for complex organic chemistry queries.
Prepare a case study on structured chemistry data
Draft a brief document or presentation explaining your experience with scientific information systems. Describe how you have previously organized or retrieved chemistry data, such as chemical structures, reaction pathways, or taxonomies, and how this structure impacts searchability.
Design a sample test dataset
Construct a small, representative dataset of organic chemistry questions and expected answers. Include edge cases, such as ambiguous nomenclature or complex reaction conditions, to demonstrate your ability to identify potential failure points in AI-driven search connectors.
Formulate technical questions for the interview
Prepare specific questions regarding the current architecture of Reaxys, the specific challenges the team faces with agentic connectors, and how the cross-functional workflow between chemistry experts and data scientists is structured.
Availability last checked: 18 Oct 2026. Status can change after a check; confirm on the employer’s website. Report an issue · Our checking policy
Share this opportunityKnow someone who would be a great fit?