Software Engineer, Model Evaluation Systems

Build and optimize model evaluation systems to ensure that AI models deployed on Groq’s platform achieve best-in-class quality, throughput, and efficiency. Develop benchmarking frameworks, optimize model performance, and drive improvements that push the boundaries of evaluation systems. Responsibilities include: Software Development: Write simple, concise, high-performance code in Python and Golang to support evaluation pipelines and tooling. Model Evaluation & Benchmarking: Develop and implement benchmarking tools to assess the performance of models hosted on Groq. Automation & Tooling : Build automated evaluation systems and testing infrastructure to streamline model deployment and validation processes. System Integration & Testing: Work closely with cross-functional teams to integrate models into Groq’s infrastructure. Data-Driven Insights: Collect and analyze performance data, providing actionable insights and recommendations for improving model performance, scalability, and reliability.