Senior Engineer, Competitive Benchmarking & Performance

About the role

Elastic, the Search AI Company, enables everyone to find the answers they need in real time, using all their data, at scale — unleashing the potential of businesses and people. The Elastic Search AI Platform, used by more than 50% of the Fortune 500, brings together the precision of search and the intelligence of AI to enable everyone to accelerate the results that matter. By taking advantage of all structured and unstructured data — securing and protecting private information more effectively — Elastic’s complete, cloud-based solutions for search, security, and observability help organizations deliver on the promise of AI.

What is The Role

Elasticsearch powers search, observability, and AI retrieval (RAG) for the world's largest organizations. We are seeking a Senior Software Engineer to lead competitive benchmarking initiatives within the Elasticsearch Performance team.

You will develop representative workloads, automate reproducible experiments, and investigate how Elasticsearch compares with alternative systems. Your work will identify performance strengths, gaps, and tradeoffs, guide engineering improvements, and help customers make informed technical decisions.

This is a hands-on engineering role focused on building benchmarks and investigating performance, with technical publishing as a shared responsibility alongside engineering and content partners.

A typical investigation might ask how Elasticsearch and an alternative system compare under concurrent ingestion and hybrid search, at comparable retrieval quality and cost, and which engineering changes would improve the outcome. This role offers the opportunity to connect deep performance analysis with product improvements and public technical work.

What You Will Be Doing

- Own prioritized competitive benchmarking initiatives across search, vector and hybrid retrieval, and analytical and observability workloads.

- Build and maintain automated benchmark harnesses, datasets, query sets, and load profiles that reflect real-world usage, including concurrent ingestion and querying.

- Design fair comparisons with documented system versions, configurations, tuning decisions, resource budgets, and functional differences.

- Evaluate latency distributions, throughput, resource consumption, and cost efficiency. For retrieval workloads, measure performance at comparable recall or relevance targets.

- Adapt and extend workload-appropriate tools such as Elasticsearch Rally, ClickBench, and vector search benchmark frameworks.

- Investigate performance differences using profiling, system metrics, and controlled experiments; collaborate with engineering teams to identify causes and validate improvements.

- Evaluate relevant self-managed and managed cloud deployments, including serverless offerings, accounting for scaling behavior and service constraints.

- Work with engineering and technical content partners to publish reproducible benchmark artifacts and clear technical reports that explain methodology, findings, limitations, and tradeoffs.