Autonomy Data Engineer II – Data Lake & Pipelines

Torc Robotics; Blacksburg (VA); Hybrid; USD 139,000 - 167,000; Full time

Benefits offered by this job

Bonus component

Stock options

Medical premiums

Dental premiums

Vision premiums

401K match

Flexible schedule

Paid vacation

Holiday closures

AD&D & Life Insurance

Job summary

Torc Robotics is seeking an Autonomy Data Engineer Level 2 to design, build, and operate the data infrastructure powering our autonomy program. You will create pipelines, storage, and tooling to turn raw vehicle sensor logs into curated datasets for perception, planning, and simulation teams.

This high-ownership role handles large-scale sensor data from vehicles in demanding environments, enabling model training and rapid data insights with cross-functional collaboration across data science and

Qualifications

• Bachelors in CS/CE/SE/EE with 4+ years data engineering or a Master’s with 2+ years.
• Strong Python and SQL, ability to build production data pipelines.
• Experience with AWS data infra and IaC tools (Terraform, CloudFormation).
• Solid understanding of data partitioning and columnar formats (Parquet, Orc).
• Experience building data pipelines for time-series and binary data.
• Familiarity with open-source tooling and data quality monitoring.
• Experience with autonomous vehicles, robotics, or sensor-driven systems.
• Deep experience with Foxglove or Rerun for log review/QA.
• MCAP CLI or Python library for converting MCAP data to columnar formats.
• Data curation for ML training (diversity sampling, pseudo-labeling).

Responsibilities

• Design and organize program data lake schema, partitioning, and metadata indexing.
• Build end-to-end pipelines ingesting high-bandwidth sensor logs into cloud storage with reliability.
• Implement data validation, integrity checks, and retention policies.
• Build tooling to query raw logs and produce curated training/evaluation datasets.
• Automate pseudo-labeling workflows at data ingest scale.
• Develop data quality metrics and model performance indicators for labeling focus.
• Deploy and maintain data visualization tooling for log review and QA.
• Create integrations between visualization tooling and the data lake for easy data tracing.
• Collaborate with autonomy engineers to surface custom visualization panels and metrics.
• Build dashboards showing data coverage by terrain, environment, and region.
• Document data contracts and collaborate across data lifecycle teams.

Skills

Python

SQL

Data pipelines

AWS

Terraform

CloudFormation

Parquet/columnar

Time-series data

Open-source tooling

Data quality monitoring

Autonomous vehicles

Foxglove/Rerun

MCAP

MCAP tooling

Data curation for ML

Education

Bachelor’s degree in CS/CE/SE/EE

Master’s degree

Tools

Foxglove

Rerun

MCAP CLI

MCAP library

Job description

Torc Robotics is seeking an Autonomy Data Engineer Level 2 to design, build, and operate the data infrastructure powering our autonomy program. You will create pipelines, storage, and tooling to turn raw vehicle sensor logs into curated datasets for perception, planning, and simulation teams.

This high-ownership role handles large-scale sensor data from vehicles in demanding environments, enabling model training and rapid data insights with cross-functional collaboration across data science and