Ekrem Sarı

Ekrem is an AI Researcher and Data Scientist at AIMultiple. He designs and runs hands-on benchmarks for AI and LLM systems.

Professional Experience

At AIMultiple, Ekrem benchmarks end-to-end AI systems and builds the data workflows and dashboards used to track benchmark and product metrics. His benchmarks cover embedding and reranker models, vector and graph databases, inference engines, quantization, GPU concurrency and multi-GPU scaling, cloud GPU pricing and providers, text-to-SQL, and RAG and agentic RAG frameworks.

Before AIMultiple, he worked as a Data Scientist at Yandex, where he queried and analyzed large datasets with SQL to evaluate search and ranking quality against detailed guidelines.

Research Interest

Ekrem's work focuses on measuring how LLM and retrieval systems perform in practice. He designs the test harness, runs the workloads on real hardware, and compares models, frameworks, and infrastructure on accuracy, throughput, latency, cost, and scalability, across the stack from embedding models and vector databases to inference engines and GPU infrastructure. His MSc thesis automates systematic literature reviews with a RAG-based pipeline.

Education

Ekrem holds an MSc in Management Information Systems from Başkent University, where his thesis automated systematic literature reviews with a RAG-based pipeline, and is pursuing a second MSc in Data and Knowledge Engineering at Hacettepe University.