Robotics Data Engineer

Veriipro; Warren (MI); On-site; USD 110,000 - 150,000; Full time

Job summary

Veriipro is seeking a Robotics Data Engineer to design and scale ML data pipelines for robotic vision, sensor data, and multimodal datasets, supporting perception, grasping, and manipulation AI. The role emphasizes hands-on Python development, production ML pipelines, robotics simulation (Isaac Sim) and Sim2Real workflows, plus collaboration with cross-functional AI teams.

You will help manage dataset versioning, data quality metrics, and leverage Azure data services and ML frameworks such as

Qualifications

• 3+ years in data engineering, ML systems, or robotics.
• Build production-grade ML data pipelines.
• Strong Python for data processing and pipelines.
• Handle large-scale multimodal datasets (vision, sensor).
• Support robotics perception, grasping, or manipulation AI.
• Familiar with Isaac Sim or similar simulators.
• Experience in Sim2Real workflows.
• Data labeling tools and annotation workflows at scale.
• Hands-on TensorFlow and/or PyTorch.
• Azure data services exposure.

Responsibilities

• Design scalable data pipelines for robotic vision and sensor datasets.
• Build infrastructure for high-throughput data capture from robots and simulators.
• Develop semi-supervised and self-supervised labeling workflows.
• Enable Sim2Real data workflows including domain randomization.
• Manage dataset versioning, metadata, and governance for ML training.
• Collaborate with Robotics Perception, Grasping AI, and Simulation teams.
• Establish and monitor data quality metrics linked to model performance.

Skills

ML data pipelines

Python

Multimodal datasets

Robotics perception

Isaac Sim

Sim2Real

TensorFlow/PyTorch

Azure data services

Data labeling workflows

Self-supervised learning

Collaboration

Robotics experience

Data engineering

Tools

Isaac Sim

TensorFlow

PyTorch

Azure data services

Data labeling tools

Job description

Job Summary

We are seeking a Robotics Data Engineer with strong experience in machine learning data pipelines, robotics perception systems, and multimodal datasets. The ideal candidate will build scalable data infrastructure to support robotic vision, grasping, manipulation AI, and simulation-to-real (Sim2Real) workflows.

This role requires hands-on Python development, production ML pipeline experience, robotics simulation exposure, and collaboration with cross-functional AI and robotics teams.

Required Technical / Functional Skills

• 3+ years of experience in Data Engineering, Machine Learning Systems, Robotics, or related fields
• Experience building production-grade ML/AI data pipelines
• Strong Python programming skills (data processing & pipeline development)
• Experience handling large-scale multimodal datasets (vision, depth, tactile, sensor data)
• Direct experience supporting robotics perception, grasping, or manipulation AI
• Familiarity with robotics simulation platforms (e.g., Isaac Sim)
• Experience with synthetic data generation and Sim2Real workflows
• Experience with data labeling tools and annotation workflows at scale
• Hands-on knowledge of TensorFlow and/or PyTorch
• Experience with Microsoft data ecosystem (Azure data services, Power BI)
• Exposure to self-supervised or weakly supervised learning techniques
• Strong collaboration and systems-thinking mindset

Roles & Responsibilities

• Design and implement scalable data pipelines for robotic vision and sensor datasets
• Build infrastructure for high-throughput data capture from robots and simulation environments
• Develop semi-supervised and self-supervised data labeling workflows
• Enable Simulation-to-Real (Sim2Real) data workflows including domain randomization
• Manage dataset versioning, metadata, and data governance for ML model training
• Collaborate with Robotics Perception, Grasping AI, and Simulation teams
• Establish and monitor data quality metrics aligned with AI model performance

Technologies / Environments

• Python
• Machine Learning Data Systems
• TensorFlow / PyTorch
• Robotics Perception & Manipulation AI
• Isaac Sim (or similar simulation platforms)
• Azure Data Services
• Multimodal Robotics Datasets