Staff Research Engineer - Vision-Language Robotics

XDOF; San Mateo (CA); Hybrid; USD 140,000 - 200,000; Full time

Benefits offered by this job

Equity

Health benefits

Flexible work

Collaborative culture

Impactful work

Job summary

XDOF, in San Mateo, is seeking a Research Engineer/Scientist to lead data-driven efforts at the intersection of vision-language models and robot learning. You will build systems that convert raw egocentric and teleoperation video into high-signal training data for VLMs and increasingly contribute to the models themselves.

You'll drive research into what makes robot data useful—discovering metadata and annotations to unlock cross-embodiment transfer, curriculum generation, and world models.

Qualifications

• MS or PhD in Computer Science, Robotics, Machine Learning or related field from a top program
• 3–7 years of research or applied research experience in vision-language models, video understanding, robot learning, or generative modeling
• Deep fluency in PyTorch and experience with distributed training, mixed precision, and large batch workflows
• Published work or demonstrable impact in VLMs/VLAs, video representation learning, imitation learning, or related areas
• Strong engineering fundamentals and ability to design clean systems, not just run experiments

Responsibilities

• Design and implement vision-language pipelines for egocentric and teleoperation video: structured captioning, temporal grounding, action-conditioned scene understanding, and semantic annotation at scale
• Develop and evaluate representations bridging vision, language, and robot action
• Build and improve data curation systems that assess quality, diversity, and coverage of large-scale robot demonstration datasets
• Work hands-on with bimanual and high-DoF manipulation data, including real teleoperation footage and sim-generated rollouts
• Collaborate with partner labs to define data requirements and optimize data quality for downstream policy performance
• Stay current on research frontier and translate insights into production systems

Skills

Vision-language models

PyTorch

Robot learning

Video understanding

Distributed training

Data pipelines

Research experience

Education

MS or PhD in Computer Science, Robotics, ML

Tools

Large-scale training infra

Job description

XDOF, in San Mateo, is seeking a Research Engineer/Scientist to lead data-driven efforts at the intersection of vision-language models and robot learning. You will build systems that convert raw egocentric and teleoperation video into high-signal training data for VLMs and increasingly contribute to the models themselves.

You'll drive research into what makes robot data useful—discovering metadata and annotations to unlock cross-embodiment transfer, curriculum generation, and world models.