Member of Technical Staff - Robot Learning

Warp•South San Francisco, CA

About The Position

Warp Sciences is building automated laboratory infrastructure that combines AI, robotics, and life sciences to help researchers discover medicines faster. The Member of Technical Staff, Robot Learning will build learning systems that enable robots to learn and reliably perform scientific tasks in complex laboratory environments. The role owns the loop from expert demonstrations and robot experience through policy training, evaluation, and deployment, collaborating across robot learning, data, controls, hardware, and chemistry. The position develops and adapts robot-learning methods and models for precise, contact-rich manipulation; builds systems and infrastructure for large-scale multimodal robot data; deploys policies on real robotic systems; and investigates failures across the complete system. Success means establishing a repeatable cycle from expert demonstrations and robot experience to training, evaluation, and deployment, measurably improving reliability on real chemistry tasks and helping robots generalize across materials, equipment, and laboratory conditions.

Requirements

  • Strong foundations in machine learning, deep learning, and robot learning.
  • Experience with post-training, imitation learning, reinforcement learning, behavior cloning, or fine-tuning learned policies.
  • Experience training, adapting, and debugging modern deep learning models using frameworks such as PyTorch or JAX.
  • A track record of designing rigorous experiments and producing measurable improvements in model or policy behavior.
  • Strong intuition for data quality and composition, including identifying needed model experience, insufficient data, and efficient ways to improve it.
  • Experience building data pipelines, training systems, or evaluation infrastructure for multimodal or robotics data.
  • Experience working with real-world robotic systems, or a strong track record building learned systems that interact with complex physical environments.
  • Ability to investigate failures across the complete system rather than treating the model, data, controls, and hardware as separate problems.
  • High ownership and enthusiasm for problems where neither the requirements nor the right technical approach are obvious.

Nice To Haves

  • Experience with world models, world-action models, or vision-language-action models.
  • Experience post-training or adapting large pretrained models for robotics.
  • Experience with large-scale multimodal datasets, dataset curation, and distributed training.
  • Experience with imitation learning, behavior cloning, reinforcement learning, or offline RL.
  • Experience learning from human demonstrations, teleoperation data, or real-world robot experience.
  • Experience with diffusion policies, action chunking, or other modern visuomotor policy architectures.
  • Experience with dexterous, precise, or contact-rich manipulation.
  • Experience with multimodal representations spanning vision, language, actions, sensors, and robot state.
  • Experience with simulation, sim-to-real transfer, or synthetic robot data.
  • Experience with real-world robot evaluation, benchmarking, and failure analysis.

Responsibilities

  • Develop mid- and post-training methods for robot policies using real-world demonstrations, robot experience, and task-specific data.
  • Build systems that learn from expert chemists and turn demonstrations of scientific procedures into capabilities robots can reproduce and generalize.
  • Develop and adapt world models, world-action models, vision-language-action models, and other learned representations for precise, contact-rich manipulation.
  • Build training and evaluation systems to ingest, process, curate, and learn from large-scale multimodal robot datasets.
  • Deploy policies on real robotic systems and diagnose failures across models, data, perception, controls, hardware, and task design.
  • Connect data collection, training, evaluation, and deployment; determine needed data or training interventions, measure their effectiveness, and use deployment outcomes to improve subsequent iterations.
  • Partner with chemists, hardware engineers, infrastructure engineers, and robot operators to design tasks, collect useful experience, and translate research advances into dependable laboratory capabilities.
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service