LMArena
Senior Software Engineer, Data Infrastructure
LMArena, San Francisco, California, United States, 94199
Senior Software Engineer, Data Infrastructure
Location:
SF Bay Area/Remote
Type:
Full-Time
About the Role LMArena is seeking a Software Engineer to build the data infrastructure that powers real‑world AI evaluation. You’ll design and build data pipelines that process and analyze over 3 million user vote data, directly impacting how we evaluate AI model performance. The role is ideal for someone who thrives in fast‑moving environments and wants to build products that ensure accurate and fair evaluation of human preferences across models.
As an early member of our data engineering team, you’ll partner closely with researchers, engineers, and product leadership to retrieve valuable data and insights from human votes and feedback. You’ll help us move fast while staying rigorous, improving data quality, scaling our infrastructure, and deepening our ability to compare frontier models and predict human preferences.
Responsibilities
Design and build robust data pipelines to ingest, process, and transform user vote data into features essential for model performance evaluation.
Collaborate with researchers and product leadership to understand product goals and required data.
Design and implement solutions to generate result dashboards and reports, providing useful information to the public, model providers, and researchers.
Ensure the integrity, data quality, and reliability of the pipelines.
Scale our data infrastructure to accommodate increasing data volumes and evolving analytical needs.
Requirements
Strong software engineering background with a dedicated focus on data engineering and big data technologies.
Proficiency in SQL and at least one programming language commonly used for data analysis (Python (preferred), Scala, R).
Hands‑on experience with data processing and pipeline frameworks (Apache Spark, Ray Data, etc.) and at least one popular big data analytics platform (Databricks, Snowflake).
Demonstrated experience in designing, implementing, optimizing, and debugging production data pipelines.
Preferred Qualifications
Prior work in data analytics or data‑lake platforms.
Experience in advanced data analysis tools, such as Delta Lake and streaming tables.
Exposure to machine learning is a plus.
What We Offer
210k – 250k + equity. Actual compensation will depend on knowledge, skills, experience, and location.
Competitive salary and meaningful equity.
Comprehensive healthcare coverage (medical, dental, vision).l>
The opportunity to work on cutting‑edge AI with a small, mission‑driven team.
A culture that values transparency, trust, and community impact.
Why Join Us Trusted by organizations like Google, OpenAI, Meta, xAI, and more, LMArena is rapidly becoming essential infrastructure for transparent, human‑centered AI evaluation at scale. With over one million monthly users and growing developer adoption, our impact guides the next generation of safe and aligned AI systems. Our work is referenced by industry leaders and directly influences AI reliability across top‑tier industries.
#J-18808-Ljbffr
SF Bay Area/Remote
Type:
Full-Time
About the Role LMArena is seeking a Software Engineer to build the data infrastructure that powers real‑world AI evaluation. You’ll design and build data pipelines that process and analyze over 3 million user vote data, directly impacting how we evaluate AI model performance. The role is ideal for someone who thrives in fast‑moving environments and wants to build products that ensure accurate and fair evaluation of human preferences across models.
As an early member of our data engineering team, you’ll partner closely with researchers, engineers, and product leadership to retrieve valuable data and insights from human votes and feedback. You’ll help us move fast while staying rigorous, improving data quality, scaling our infrastructure, and deepening our ability to compare frontier models and predict human preferences.
Responsibilities
Design and build robust data pipelines to ingest, process, and transform user vote data into features essential for model performance evaluation.
Collaborate with researchers and product leadership to understand product goals and required data.
Design and implement solutions to generate result dashboards and reports, providing useful information to the public, model providers, and researchers.
Ensure the integrity, data quality, and reliability of the pipelines.
Scale our data infrastructure to accommodate increasing data volumes and evolving analytical needs.
Requirements
Strong software engineering background with a dedicated focus on data engineering and big data technologies.
Proficiency in SQL and at least one programming language commonly used for data analysis (Python (preferred), Scala, R).
Hands‑on experience with data processing and pipeline frameworks (Apache Spark, Ray Data, etc.) and at least one popular big data analytics platform (Databricks, Snowflake).
Demonstrated experience in designing, implementing, optimizing, and debugging production data pipelines.
Preferred Qualifications
Prior work in data analytics or data‑lake platforms.
Experience in advanced data analysis tools, such as Delta Lake and streaming tables.
Exposure to machine learning is a plus.
What We Offer
210k – 250k + equity. Actual compensation will depend on knowledge, skills, experience, and location.
Competitive salary and meaningful equity.
Comprehensive healthcare coverage (medical, dental, vision).l>
The opportunity to work on cutting‑edge AI with a small, mission‑driven team.
A culture that values transparency, trust, and community impact.
Why Join Us Trusted by organizations like Google, OpenAI, Meta, xAI, and more, LMArena is rapidly becoming essential infrastructure for transparent, human‑centered AI evaluation at scale. With over one million monthly users and growing developer adoption, our impact guides the next generation of safe and aligned AI systems. Our work is referenced by industry leaders and directly influences AI reliability across top‑tier industries.
#J-18808-Ljbffr