Build and maintain reproducible research infrastructure for evaluating digital-twin and large language model systems. Responsibilities include automating experiments, implementing deterministic measurement pipelines, managing versioned datasets and human-participant data, maintaining research-production alignment, monitoring evaluation validity and compute costs, and supporting documented coding workflows. The role requires strong Python, data pipeline, cloud, concurrency, machine learning, and software engineering skills, with preferred experience in LLM systems, model fine-tuning, inference serving, experiment tracking, and generative agents.

As a Backend Engineer, you will design and optimize backend services, APIs, and data processing, collaborating with leadership and users.

Design and develop frontend interfaces using React and Next.js, lead projects, and enhance user experiences through collaboration with founding team and users.