Job Description

Position Overview

In this role, you will work on the research, training, optimization, and real-world deployment of embodied AI models, including Vision-Language-Action (VLA) models, World Models, and related robotics foundation models.

You will work across multimodal perception, robot control, long-horizon task planning, large-scale robot data, and model deployment. This is a highly hands-on role that involves both model development and real-world robotic system integration.

Key Responsibilities

Embodied AI Model Development

Research and develop Vision-Language-Action (VLA), World Model, and other embodied AI foundation models.

Work on areas including:

Robotic manipulation

Multimodal perception and control

Long-horizon task planning

Vision-language-action reasoning

Robot-environment interaction

Develop and optimize models for real-world robotic applications.

Translate research ideas into practical models and systems that can operate reliably on physical robots.

Foundation Model Training & Optimization

Train and optimize embodied AI foundation models using large-scale real-robot datasets and egocentric human demonstration data.

Design approaches for incorporating multimodal inputs such as:

Vision

Force

Tactile sensing

Proprioception

Other robot and environmental signals

Develop and evaluate multimodal fusion architectures.

Conduct model training, evaluation, benchmarking, and performance optimization.

Analyze model performance and identify opportunities to improve training efficiency, generalization, and real-world performance.

Robotics Data Pipeline

Build and improve large-scale robotics data pipelines for model training.

Develop processes for:

Data cleaning

Data filtering

Resampling

Data augmentation

Data quality evaluation

Design scalable data pipelines capable of supporting large volumes of robot and human demonstration data.

Work closely with data and robotics teams to improve dataset quality and training efficiency.

Model Deployment & Real-Robot Testing

Deploy trained models to physical robot systems.

Perform real-world robot debugging, testing, and performance optimization.

Diagnose issues across models, sensors, software, and robotic hardware.

Iterate between model training and real-world testing to improve system performance.

Help ensure models operate reliably and consistently in real-world environments.

Qualifications

Required

1+ years of relevant industry or research experience in machine learning, robotics, computer vision, embodied AI, or a related field.

Strong understanding of deep learning and modern machine learning methods.

Experience with PyTorch or similar deep learning frameworks.

Experience training and evaluating machine learning models.

Strong programming skills in Python and familiarity with relevant ML/robotics tooling.

Understanding of multimodal learning, computer vision, robotics, or related areas.

Ability to work in a fast-paced startup environment and take ownership of technical problems from research through implementation.

Strong problem-solving and debugging skills.

Strong Plus

Real-World Robotics Deployment

Experience deploying and debugging machine learning models on physical robot systems.

Ability to bring models from development into real-world robotic environments.

Experience troubleshooting and stabilizing robotic systems in production or experimental environments.

Multimodal / VLA Models

Experience working with force, tactile, or other multimodal sensing.

Experience designing or training multimodal fusion models.

Hands-on experience with VLA models, including model design, training, evaluation, or real-world applications.

Experience with robotic manipulation or embodied AI systems.

Large-Scale Distributed Training

Experience with large-scale distributed model training.

Familiarity with DDP, DeepSpeed, FSDP, or similar distributed training frameworks.

Experience optimizing training performance, GPU utilization, memory usage, or training throughput.

Experience working with large-scale datasets and distributed data pipelines.

Embodied AI / VLA Research Engineer