VLA Algorithm Engineer – Simulation Data Generation & World Models

Description

The company is building embodied AI foundation models and is looking for a VLA Algorithm Engineer who works across robotics, simulation and world models.

The work covers building robotic simulation environments, creating large-scale synthetic training data pipelines, and improving how models trained in simulation carry over to real robots.

A good fit enjoys hard problems in robotics, reinforcement learning, imitation learning and 3D vision, and wants to help make robotic systems more capable, robust and generalizable.

Responsibilities

• Build and optimize simulation environments for robotic tasks such as manipulation, navigation, mobile manipulation and humanoid robotics.
• Help train and optimize embodied AI foundation models, including pretraining on large-scale egocentric human video and real-world robot data.
• Design ways to bring in multimodal inputs, including force and tactile sensing, and develop, train, evaluate and optimize models that use these signals.
• Improve simulation and evaluation pipelines to shrink the sim-to-real gap and improve model stability, robustness and generalization in real-world settings.

Requirements

• At least 1 year of relevant professional or research experience in robotics, simulation, system identification, reinforcement learning (RL), imitation learning (IL), world models, 3D vision or a closely related field.
• Experience with robotics simulation, robotic learning or related algorithm development.
• A solid understanding of at least one research area such as reinforcement learning, imitation learning, system identification, world models or 3D computer vision.
• Preferred: hands-on experience developing or extending simulation platforms, with familiarity with the internals of tools such as NVIDIA Isaac Sim, Isaac Orbit, MuJoCo, PyBullet or Genesis.
• Preferred: experience building synthetic datasets for robotics or computer vision, designing scalable data generation pipelines, or using diffusion models to generate synthetic data at scale.
• Preferred: proven record of moving reinforcement learning or imitation learning policies from simulation to physical robotic arms or mobile robots. Experience handling simulation-to-reality differences in dynamics and observations through systematic compensation or adaptation is a plus.

Conditions

The posting does not state a location, work model, schedule or contract type.

Benefits

• Health insurance
• Vision care
• Dental coverage
• 401(k)
• Paid holidays
• PTO (Paid Time Off)
• Sick leave