Member of Technical Staff — AI Training & Sandbox Systems

Dex; Greater London; On-site; GBP 100,000 - 140,000; Full time

Job summary

Dex is partnering with a frontier AI lab in London and Paris seeking a Member of Technical Staff to own post‑training and harness loops. You will work between research and systems engineering, shaping bets, tuning models, and building the sandboxed execution harnesses for agent testing against complex tasks.

Responsibilities span SFT, RL, and RLHF, with emphasis on production-grade Python, scalable data pipelines, and rigorous evaluation.

Qualifications

• Proven track record directly training or fine‑tuning models (SFT, RL, or RLHF).
• Strong foundations in ML, RL architectures, and evaluation.
• Production‑grade Python engineering with modular, observable systems.
• Experience turning ambiguous problems into working systems over months.
• Willing to relocate to London or Paris.

Responsibilities

• Design and execute end‑to‑end post‑training pipelines using SFT and RL.
• Architect sandboxed execution environments and deterministic feedback loops.
• Build and scale training-data infrastructure and curated datasets.
• Establish evaluation frameworks to benchmark capabilities and reproducibility.
• Provide technical leadership across ambiguous research directions with engineers.

Skills

ML training

Reinforcement learning

Python engineering

System design

Leadership

RLHF

PyTorch

Tools

PyTorch

TensorFlow

Job description

Dex is partnering with a frontier AI lab in London and Paris seeking a Member of Technical Staff to own post‑training and harness loops. You will work between research and systems engineering, shaping bets, tuning models, and building the sandboxed execution harnesses for agent testing against complex tasks.

Responsibilities span SFT, RL, and RLHF, with emphasis on production-grade Python, scalable data pipelines, and rigorous evaluation.