Job Description

Design the next benchmarks and RL environments for evaluating AI reliability. Build and maintain evaluation datasets and RL environments used by frontier AI labs and startups across finance, healthcare, and legal. Create expert-curated training data, calibrated rubrics, and long-horizon RL tasks. Work in Aptura AI's small London-based team and ship solutions directly to customers. This role focuses on Applied AI; collaboration with researchers and engineers to translate requirements into robust benchmarks and tools. This posting covers two MTS tracks at Aptura AI. Apply via the provided link.