1X Technologies AS-posted 7 days ago
$180,000 - $300,000/Yr
Full-time
Onsite • Palo Alto, CA
101-250 employees

You will build large multi-modal generative “world models” that predict future sensor inputs and robot actions based on past observations. These foundational models enable robots to understand and operate effectively in unstructured, real-world environments. You’ll work across data pipelines, model architectures, and deployment to drive improvements in robot autonomy. This role combines cutting-edge research with hands-on product development to push the limits of robot intelligence.

  • Build full-stack systems across data engineering, model architecture, and product delivery
  • Develop high-throughput data loaders for large-scale, multi-modal robot datasets
  • Implement tokenizers and transformers designed for web-scale robotic data
  • Improve robot autonomy by advancing world model architectures
  • Predict robot performance in the real world based on pre-training metrics such as log loss
  • Strong experience with Python and related tools such as Bazel
  • Proficiency with PyTorch or equivalent deep learning frameworks
  • Familiarity with simulation platforms such as Isaac Sim or MuJoCo
  • Experience working with multi-modal generative models combining video, audio, text, and action prediction
  • Ability to design and optimize large-scale data pipelines for training
  • Understanding of scaling laws and performance metrics for foundation models
  • Health, dental, and vision insurance
  • 401(k) with company match
  • Paid time off and holidays
© 2024 Teal Labs, Inc
Privacy PolicyTerms of Service