Ekrem Sarı
Ekrem is an AI Researcher and Data Analyst 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 an Assessor at Yandex, where he evaluated search quality and labeled large volumes of data against detailed guidelines to support ranking and model quality.
Research Interest
Ekrem's work focuses on the MLOps and LLMOps lifecycle and on measuring the performance of AI systems. He compares models, frameworks, and infrastructure on metrics such as accuracy, throughput, API cost, and scalability, across the stack from embedding models and vector databases to GPU and cloud infrastructure. His MSc thesis automates systematic literature reviews with a RAG-based pipeline.
Education
Ekrem holds a BA from Hacettepe University and is completing an MSc at Başkent University.
Latest Articles from Ekrem
RAG Evaluation Tools: Weights & Biases vs Ragas vs DeepEval
When a RAG pipeline retrieves the wrong context, the LLM confidently generates the wrong answer. Context relevance scorers are the primary defense. We benchmarked five tools across 1,460 questions and 14,600+ scored contexts under identical conditions: same judge model (GPT-4o), default configurations, and no custom prompts. Under standard conditions, WandB, TruLens, and Ragas emerged as…
Remote Browsers: Web Infra for AI Agents Compared
AI agents rely on remote browsers to automate web tasks without being blocked by anti-scraping measures. The performance of this browser infrastructure is critical to an agent’s success. We benchmarked 8 providers on success rate, speed, and features. To do this, we executed 160 automated tasks, running 4 distinct scenarios 5 times for each service…
Top Vector Database for RAG: Qdrant vs Weaviate vs Pinecone
Vector databases power the retrieval layer in RAG workflows by storing document and query embeddings as high‑dimensional vectors. They enable fast similarity searches based on vector distances. We benchmarked six vector database providers, focusing on their pricing structures and performance: Vector database comparison: Pricing & performance In this benchmark, we used: 1 million vector dataset…
Graph Database Benchmark: Neo4j vs FalkorDB vs Memgraph
We benchmarked Neo4j, FalkorDB, and Memgraph on a synthetic graph derived from 120,000 Amazon product reviews (381K nodes, 804K edges). We ran 12 query templates with 1,000 measurements each, tested ingestion at 6 batch sizes, sustained concurrent load for 60 seconds at up to 32 threads, and measured memory, cold start, mixed workload, and index…
Cloud GPU Pricing, Performance & Provider Comparison
Cloud GPU list prices for the same model can differ several times over from one provider to another. We curated the lowest rate, provider, market range, and median for 40+ GPU configurations across all three pricing tiers, plus a throughput-per-dollar benchmark on 10 models. Cloud GPU price per throughput See the most cost-effective GPU for…
Top 20+ Agentic RAG Frameworks
Agentic RAG enhances traditional RAG by boosting LLM performance and enabling greater specialization. We conducted a benchmark to assess its performance on routing between multiple databases and generating queries. Explore agentic RAG frameworks and libraries, key differences from standard RAG, benefits, and challenges to unlock their full potential. Agentic RAG benchmark: Multi-database routing and query…
LLM Inference Engines: vLLM vs LMDeploy vs SGLang
We benchmarked 3 leading LLM inference engines on NVIDIA H100: vLLM, LMDeploy, and SGLang. Each engine processed identical workloads: 1,000 ShareGPT prompts using Llama 3.1 8B-Instruct to isolate the true performance impact of their architectural choices and optimization strategies. EnginesBest for vLLM-Prototyping and experimentation across 100+ model architectures -Multi GPU environments (NVIDIA, AMD, Intel) LMDeploy-Production…
GPU Concurrency Benchmark: H100 vs H200 vs B200 vs MI300X
I have spent the last 20 years focusing on system-level computational performance optimization. We benchmarked the latest NVIDIA GPUs, including the NVIDIA’s H100, H200, and B200, and AMD’s MI300X, for concurrency scaling analysis. Using the vLLM framework with the gpt-oss-20b model, we tested how these GPUs handle concurrent requests, from 1 to 512. By measuring…
Text-to-SQL: Comparison of LLM Accuracy
I have relied on SQL for data analysis for 18 years, beginning in my days as a consultant. Translating natural-language questions into SQL makes data more accessible, allowing anyone, even those without technical skills, to work directly with databases. We used our text-to-SQL benchmark methodology on 35+ large language models (LLMs) to assess their performance…
Best RAG Tools, Frameworks, and Libraries
RAG improves LLM responses by grounding them in external data instead of just what the model memorized in training. We benchmarked the components a RAG system is built from and gathered the results in one place, with a practical guide to choosing each part of the stack. See our benchmark results for each RAG component,…
AIMultiple Newsletter
1 free email per week with the latest B2B tech news & expert insights to accelerate your enterprise.