Research Scientist, Dexterous Manipulation & Robot Learning

Lila Sciences Lila Sciences · AI Frontier · One Charles Park, Cambridge, MA · Robotics

Research Scientist role focused on developing autonomous robotic systems for scientific discovery. This involves pioneering manipulation algorithms using foundation models, RL, diffusion, and human guidance. The role also focuses on human-robot interaction, multi-modal perception, and designing autonomous systems with trust calibration.

What you'd actually do

  1. Pioneering approaches for precise and dexterous robotic manipulation that leverage foundation models, reinforcement learning, diffusion-based methods, and human guidance to enable adaptive and intelligent robotic systems capable of complex tasks across diverse scientific environments
  2. Developing novel human-robot interaction frameworks that incorporate imitation learning, and learning from human guidance, feedback, demonstrations and corrections, creating intelligent robotic agents that can seamlessly integrate with human scientific workflows and rapidly adapt to new experimental contexts
  3. Advancing dexterous manipulation research through cutting-edge machine learning approaches, including diffusion models and adaptive learning algorithms, that synthesize multi-modal sensing (tactile, visual, language and other contextual sensing) to develop generative skill representation sand sophisticated motor learning policies for intelligent robotic systems
  4. Designing autonomous robotic systems with trust calibration mechanisms, enabling intelligent agents that can dynamically adjust their behaviors based on contextual information in complex scientific tasks

Skills

Required

  • Robotics
  • Machine Learning
  • Computer Science
  • foundation models for robotic learning
  • reinforcement learning
  • diffusion-based methods
  • imitation learning
  • adaptive learning algorithms
  • PyTorch
  • TensorFlow
  • deep learning architectures
  • foundation models
  • diffusion-based generative models
  • multi-modal perception systems
  • tactile sensing
  • visual sensing
  • language sensing
  • robot learning
  • trust calibration
  • contextual learning
  • generative robotic skill learning

Nice to have

  • foundation models in robotics
  • diffusion methods in robotics
  • large-scale machine learning model development
  • generative models
  • diffusion-based approaches
  • human-in-the-loop learning
  • correction-based training paradigms
  • diffusion-guided skill transfer
  • theoretical machine learning research
  • practical robotic implementations

What the JD emphasized

  • Ph.D. in Robotics, Machine Learning, Computer Science, or a related field with demonstrated expertise in foundation models for robotic learning
  • Advanced proficiency in reinforcement learning, diffusion-based methods, imitation learning, and adaptive learning algorithms for robotic manipulation
  • Expert-level experience with machine learning frameworks (PyTorch, TensorFlow) and deep learning architectures for developing foundation models, with specific expertise in diffusion-based generative models for robotics
  • Proven track record of developing multi-modal perception systems integrating tactile, visual, language and other contextual sensing for intelligent robotic agents
  • Strong publication record in robot learning, demonstrating innovative approaches to trust calibration, contextual learning, and generative robotic skill learning

Other signals

  • foundation models for robotic learning
  • reinforcement learning
  • diffusion-based methods
  • imitation learning
  • adaptive learning algorithms
  • multi-modal sensing
  • human-robot interaction
  • autonomous robotic systems
  • trust calibration mechanisms
  • generative skill representation
  • sophisticated motor learning policies