Robot Learning Researcher

Aktoria Robotics; San Francisco (CA); On-site; USD 150,000 - 210,000; Full time

Job summary

Aktoria Robotics, based in San Francisco, seeks a researcher to lead end-to-end robot learning efforts, focusing on training large-enabled agents, developing VLA and foundation models, and driving data-centric experiments on real robots.

The candidate will publish benchmarks and papers, contribute to scaling studies, and curate data and evaluation formats for production deployments. VISA sponsorship is possible if required.

Qualifications

• Experience training IL/VLA policies at scale.
• First-author publications (CoRL/ICRA/IROS/RSS) or equivalent strong open-source work.

Responsibilities

• Lead robot learning initiatives for VLA and foundation models.
• Train and fine-tune VLAs and robot foundation models.
• Run data-quality ablations and scaling studies.
• Publish papers and benchmarks.
• Curate data, filtering, formats, and evaluations on real robots.

Skills

IL/VLA training

First-author publications

Open-source work

Job description

• -You will lead entire robot learning (VLA/Foundation Models)
• - Train / fine-tune VLAs and robot foundation models
• - Run data-quality ablations and scaling studies
• - Publish papers and benchmarks
• - data curation, filtering, formats, evals on real robots

Expected to have:-

• -experience training IL/VLA policies at scale
• -First-author publications (CoRL/ICRA/IROS/RSS/Neur IPS) or equivalent strong open-source work .
• -If required we will sponsor VISA .

About Aktoria Robotics :-

Aktoria builds remote teleoperation software for robots. A remote operator can run a robot anywhere in the world as if standing right next to it. Our product is what makes deployed robots useful today .