Building dexterous robots that learn from human biomechanics. Backed by Y Combinator.
About the role
You will develop machine learning systems that enable robots to acquire dexterous manipulation skills from human demonstrations and multimodal sensor data. You will work across data processing, model training, evaluation, and real-world deployment, using experiments to understand what makes robots learn more effectively. Our research involves vision, motion, biomechanical signals, and robot interaction data, with applications to imitation learning, vision-language-action models, video models, and world models. Found on 1752vc Careers, the job board for startup and VC roles.
What they're looking for
- Strong programming skills in Python and experience with PyTorch, JAX, or similar machine learning frameworks
- Solid understanding of deep learning, model training, optimization, and evaluation
- Experience developing and evaluating machine learning systems beyond using pretrained models through APIs
- Ability to independently design experiments, debug training pipelines, and interpret results
- Experience in one or more areas such as computer vision, multimodal learning, generative models, representation learning, reinforcement learning, or imitation learning
- Experience with large-scale training, distributed computing, or ML infrastructure is a plus
More about this role
You will develop machine learning systems that enable robots to acquire dexterous manipulation skills from human demonstrations and multimodal sensor data. You will work across data processing, model training, evaluation, and real-world deployment, using experiments to understand what makes robots learn more effectively. Our research involves vision, motion, biomechanical signals, and robot interaction data, with applications to imitation learning, vision-language-action models, video models, and world models. We are looking for engineers with strong machine learning fundamentals and the ability to turn research ideas into working systems. Prior robotics experience is not required.
- Develop and improve training, fine-tuning, and evaluation pipelines for machine learning models using human and robot data.
- Train and adapt models for manipulation, action prediction, and learning from demonstrations.
- Explore methods for learning representations from vision, motion, and biomechanical signals.
- Experiment with imitation learning, reinforcement learning, and modern foundation models for robotic applications.
- Design experiments and ablations to understand model behavior, identify...
Browse similar: AI jobs · AI startup jobs · Startup jobs · San Francisco Bay Area