AI Engineer, Post-Training & Sandbox Systems

Dex is seeking a Member of Technical Staff to own the post-training and harness loop, bridging research and systems engineering. You will design end-to-end pipelines for supervised fine-tuning and reinforcement learning, and build sandboxed execution harnesses to test agents against complex digital tasks.

This role spans Senior to Principal levels based on depth and judgment. Based in London or Paris, you will lead production-grade Python work and translate open-ended capability goals into

#J-18808-Ljbffr…