Artificial Intelligence

This scientist will take ownership of evaluation projects from ambiguous business or customer questions through experimental design, data and metric validation, analysis, and final recommendations. The work is part of OCI’s AI Evaluation Science function and spans areas including reasoning, coding, retrieval-augmented generation, agents, multimodal systems, multilingual performance, and responsible AI. The role involves creating reusable benchmarks and pipelines, assessing quality alongside cost, latency, safety, robustness, and reliability, and validating automated and human evaluation methods. The scientist will work closely with research, engineering, product, data, annotation, and external teams while documenting assumptions and results clearly. It suits an experienced machine learning practitioner who combines strong scientific judgment with software engineering ability, independent ownership, and interest in publishable evaluation research.