Deep Learning - Robot Manipulation Engineer

Persona AI Inc•Houston, TX

8d•Onsite

About The Position

Persona AI is building humanoid robots for demanding environments in heavy industry such as shipyards, steel mills, fabrication facilities, and offshore platforms. These robots will perform tasks like welding, grinding, maintenance, inspection, and material handling, which are dangerous, physically demanding, and difficult to staff. The company is backed by strategic and financial investors and has relationships with global industrial leaders. Persona AI is looking for a Deep Learning Manipulation Engineer to train robots for real-world applications. This role offers an opportunity to shape the company's deep learning and manipulation strategy and infrastructure.

Requirements

Courage and grit to tackle some of the hardest problems in robot manipulation.
Enthusiasm for working collaboratively in fast paced ambiguous environments.
Masters or PhD in Robotics, Computer Science, or a related field.
3+ years of experience in applying deep learning to robotic manipulation.
Strong understanding and proficiency with state of the art algorithms and best-practices in behavior cloning, vision-language-action models, diffusion policies, foundation models, etc.
Experience with cloud computing and large-scale datasets.
Understanding of the challenges of deploying neural network models in the real world.
Capable of writing high quality software.
Strong first principles thinker.

Nice To Haves

Experience with other aspects of ML applied to robotics, including computer vision algorithms, sensors, point clouds, segmentation and object detection.
Published papers at top ML/Robotics conferences (ICML, ICRA, CoRL, RSS, NeurIPS).
Have deployed robots, collected large amounts of data, and trained large neural networks that work in production environments.

Responsibilities

Design and implement advanced deep learning models and training procedures to achieve dexterous manipulation for humanoid robots with high DOF and multi-fingered hands.
Train models, using curriculum learning strategies, to progress from simple object interactions to precise grasping, long-horizon tasks, tool-use, and in-hand object manipulation.
Incorporate tactile sensing and proprioception into end-to-end learning pipelines, enabling robust closed-loop policies.
Work with the teleoperation and data team to design data collection and versioning strategies.
Leverage existing state-of-the-art manipulation models and contribute to the development of new architectures for emerging complex tasks.
Deploy trained manipulation models to robotic hardware, ensuring real-time performance, safety, and integration with control systems and sensors.
Collaboratively develop and optimize the manipulation ML pipeline.
Keep up to date with the state of the art in research and development.
Develop and execute evaluation pipelines to rigorously test learned manipulation models, including real-world trials and simulation, measuring performance, robustness, and generalization across tasks and environments.
Collaborate in attracting, nurturing and growing the machine learning and autonomy teams.