Scientist & Builder
I build and lead research teams, turning advances in reinforcement learning into working systems.
I’ve worked on reasoning in Gemini, learning from demonstrations, and control systems that have to work beyond a benchmark. Away from the keyboard: surfing, sailing, climbing, and a few collective projects.
Now: Founding Research Scientist at UMA ↗
Gemini Thinking
I helped build and co-led one of the teams that contributed to Gemini Thinking, working on RL and reasoning behavior alongside the infrastructure for stable, reproducible experiments.
GPQA Diamond performance with increasing thinking budget.
Gemini 2.5 Flash announcement · April 2025 ↗
Learning models for control, exploring without a task, and transferring what an agent learns to new objectives.
Learning from demonstrations and human video.
Getting RL working for real.
RoboVQA: Multimodal Long-Horizon Reasoning for Robotics ↗Contributed to work on visual question answering and reasoning for real-world robotics.
Boats, cliffs, workshops.
Things built together.
Helped start and build a sail-training non-profit that owns Pegasus.
Visit project ↗
Co-founded the local climbing club.
Visit project ↗
Shared workshops and a collective sawmill in Nozières.
Visit project ↗
Helped start an aquatic drone non-profit and bring its drones into production.
Visit project ↗Part of the AI team building general-purpose robots that can understand and act in the physical world.
Helped build and co-led one of the teams contributing to Gemini Thinking. Worked on reinforcement learning, reasoning, and the infrastructure for reliable experimentation.
Led the real-world RL effort and projects on offline planning and learning from demonstrations. Also contributed to robotics research and applied ML collaborations in healthcare and marine biology.
Ran an independent consultancy, including robotics R&D for Nuro, where I built a complete grocery-picking demonstrator. Also worked with Air Street on technical due diligence.
A founding research scientist in DeepMind’s Applied team, working on projects including a vision-based braking watchdog for Waymo. Helped start Google’s datacenter cooling project and co-invented the patented control approach.
Also co-initiated an industrial robotics project within DeepMind.
Researched how reinforcement learning can make classifiers choose which information to acquire under a budget, with Ludovic Denoyer and Patrick Gallinari. Extended the approach to images, alongside teaching systems and introductory robotics.
Earned an engineering degree in computer science in Lyon, before moving into reinforcement learning research.
For conversations about research, building things, or shared interests.
Based in Brittany, France.
gabe@squirrelsoup.net ↗GitHub ↗
