Software Engineer, Evaluation Frontend

As an Evaluation Frontend Software Engineer, you will play a key role in helping us make modelling decisions based on experimental outcomes for our large language models (LLMs). Your primary focus will be on building tools to enable easy visualization and analysis of model evaluations which are stored in a central database. You will work closely with cross-functional teams, including researchers and engineers, to surface the insights that are necessary for the future development of our models.

This role combines expertise in statistics, data science, frontend development and data visualization.

Responsibilities

• Design tools and visualizations that enable researchers and engineers to compare and analyse hundreds of model evaluations. This includes both data visualization tools, as well as statistical tools to extract signal from the noisy signals we get.
• Develop an understanding of the relative merits and limitations of each of our model evaluations, as well as suggest new facets of model evaluation.

• Extremely strong software engineering skills.
• Strong statistical skills and experience evaluating scientific experiments related to data collection and model performance.
• Prior experience building front-end visualization systems and dashboards.
• Familiarity with ML systems evaluations.
• Proficiency in programming languages such as Python and ML frameworks (e.g., PyTorch, TensorFlow, JAX).
• Excellent communication skills to collaborate effectively with cross-functional teams and present findings.
• One or more papers at top-tier venues (such as NeurIPS, ICML, ICLR, AIStats, MLSys, JMLR, AAAI, Nature, COLING, ACL, EMNLP).