Software Engineer Data Infrastructure
ArenaVisit Arena website
Arena is a community-powered AI evaluation platform where people compare frontier-model outputs and vote, generating human-preference data and public leaderboards.
San Francisco, United States
Funding history
About Arena
Arena Intelligence, Inc. operates Arena, formerly LMArena and previously known as Chatbot Arena. Its platform measures real-world AI model performance through user comparisons, votes, leaderboards, and agentic evaluation.
Skills
About the Role
You will design and build data pipelines that ingest, process, and transform user-vote data for model evaluation. You will improve pipeline reliability and data quality, scale infrastructure, and create dashboards and reports for evaluation insights.
Requirements
- 5+ years of software engineering experience focused on data engineering and big data technologies
- SQL proficiency
- Proficiency in Python, Scala, or R
- Experience with data processing and pipeline frameworks such as Apache Spark or Ray Data
- Experience with Databricks or Snowflake
- Experience designing, implementing, optimizing, and debugging production data pipelines
Responsibilities
- Design and build data pipelines for user-vote data
- Ingest, process, and transform data into model-evaluation features
- Collaborate to identify necessary data
- Build result dashboards and reports
- Ensure pipeline integrity, data quality, and reliability
- Scale data infrastructure for growing volumes and analytical needs
Benefits
- Equity
- Medical benefits
- Dental benefits
- Vision benefits
- Additional health and wellness support programs
