Senior Data Analyst - AI Evaluation

Elsevier

Automate and conduct LLM-as-jury evaluations to improve AI-powered life sciences solutions through scientific expertise and rigorous analysis.

About our Team: We are a growing team working on the evaluation of AI systems in development and on cross-domain harmonization. Our mission is to enable better, more trustworthy AI-driven products by combining scientific expertise with rigorous evaluation and AI-ready data. We generate actionable evidence that accelerates product improvement, and we unlock greater value from curated scientific knowledge by making it interoperable, interpretable, and reliably usable by AI across domains.

About the Role: The Senior Data Analyst - AI Evaluation will support the evaluation of AI-powered solutions that use life sciences, chemistry, and regulatory data. Working with scientific domain experts, product, data science, and engineering teams, you will contribute to evaluation strategies and rubrics, evaluation scenarios, and acceptance criteria that reflect customer needs and product goals. A key focus of this role is adapting and validating automated evaluation approaches. Using an “LLM as jury” framework, you will tailor evaluation criteria and methods to specific products, use cases, and metrics. You will assess the reliability of automated judgments, identify gaps or inconsistencies, and refine the approach in collaboration with relevant experts. Through structured analysis, domain-informed judgment, and iterative validation you will contribute to more robust evidence of quality, faster feedback cycles for product development, and stronger alignment with real-world scientific and customer requirements.

Responsibilities: Contribute to customer-focused success criteria, evaluation rubrics, and acceptance criteria for AI solutions; help define evaluation scope, metrics, and scenarios using domain knowledge across drug discovery, drug development, and regulatory approval; build and curate scientific test sets and benchmarks reflecting real-world use of life sciences and regulatory data; adapt LLM-as-jury evaluation approaches to specific products, use cases, and metrics, validating and refining their performance with scientific domain experts; conduct manual and automated evaluations of AI outputs, investigate discrepancies and failure modes, and provide evidence-based feedback on evaluation quality; work closely with product, data science, and engineering teams to understand how AI systems access, interpret, and use scientific data; document evaluation findings, limitations, and recommendations clearly for cross-functional teams to support product improvements and release decisions.

Requirements: A strong academic background in life sciences (such as bioinformatics, cheminformatics, biochemistry, pharmacology, or related fields); experience evaluating AI or algorithmic outputs using scientific data; relevant Python skills to develop lightweight solutions, automate workflows, or support analytical tasks; experience applying scientific expertise in structured data or content environments such as databases, taxonomies, knowledge graphs, or similar systems; familiarity with how AI products access and use data, including a general understanding of data flows, APIs, and version-controlled workflows such as GitHub; collaborative mindset and clear communication skills.

Work in a way that works for you: We promote a healthy work/life balance across the organization. We are confident that we offer an appealing working prospect for our people, with wellbeing initiatives, family leave and tuition reimbursement to help meet immediate responsibilities and long-term goals. Working flexible hours to help you fit everything in and work when you are the most productive.

Working for you: At Elsevier, wellbeing and happiness are key to a long and successful career. Benefits include group health insurance policy (covering self and family), group life insurance/accident policy, generous long-service awards, new baby gift, subsidized food in some locations, various leave options, and transport support in some locations.

About Us: A global leader in information and analytics, we help researchers and healthcare professionals advance science and improve health outcomes for the benefit of society. Building on our publishing heritage, we combine quality information and vast data sets with analytics to support science and research, health education and interactive learning, as well as clinical practice. We are committed to providing a fair and accessible hiring process. If you have a disability or other need that requires accommodation or adjustment, please let us know by submitting our Applicant Request Support Form. We are an equal opportunity employer: qualified applicants are considered for and treated during employment without regard to race, color, creed, religion, sex, national origin, citizenship status, disability status, protected veteran status, age, marital status, sexual orientation, gender identity, genetic information, or any other characteristic protected by law.