Physical AI Engineer (Robot Learning)

Location: On site at hirify.global in Beit HaEmek, near Nahariya, northern Israel

Company

hirify.global builds autonomous robotic beekeeping systems for commercial fields.

What you will do

• Fine-tune vision-language-action policies and world models for bimanual, contact-rich manipulation, including optimization for embedded edge compute.
• Build physical simulation and digital-twin systems as scalable data sources and reduce the sim-to-real gap.
• Shape teleoperation data collection and develop tools to curate and combine real and simulated episodes.
• Evaluate policies in simulation and on physical robots, tracing failures to data, models, simulation, or hardware.
• Develop autonomous performance evaluation methods to detect abnormal behavior, identify failure modes, and trigger safe shutdown and escalation.
• Follow advances in Physical AI and robot learning and run focused experiments to assess potential approaches.

Requirements

• Advanced degree in a relevant science or engineering field.
• Strong foundations and hands-on experience training and evaluating deep learning models.
• Experience with reinforcement learning, including applications to robot learning and manipulation.
• Experience training and deploying manipulation policies on a physical robot.
• Ability to learn and explore emerging Physical AI approaches with curiosity and an open mind.
• Research-driven approach: form independent views from papers and first principles, then test them.
• Ability to scope open-ended problems and independently deliver working solutions.
• Clear and honest communication of experimental results, limitations, and lessons learned.
• Strong collaboration and communication skills across mechanical, embedded, and product teams.

Nice to have

• Hands-on experience with imitation learning, VLA models, world models, and reinforcement learning.
• Experience with edge deployment, including distillation, quantization, or inference optimization.
• Familiarity with robotics middleware.
• Familiarity with robot-learning data formats and tooling.
• Publications or open-source contributions in robotics or Physical AI.

Culture & Benefits

• Hands-on, research-oriented work in a small innovative team.
• Work spans real-world robotic systems, simulation, physical robots, and cross-functional collaboration.
• Full-time salaried employment.