Senior ML Engineer — Autonomous Trucking Data (Stock Options)

Torc Robotics; United States; Remote; USD 177,000 - 213,000; Full time

Benefits offered by this job

Stock options

Health coverage

401K matching

Flexible vacation

Company holidays

Life insurance

Job summary

Torc Robotics is seeking a data-focused engineer to architect distributed data pipelines for autonomous trucking data. You will extract and catalog safety-critical events from multi-sensor logs, using Pegasus standards and ML-assisted methods.

The role requires strong Python/SQL, Databricks experience, and cloud familiarity. You will collaborate with perception, simulation, and systems teams to define what constitutes a meaningful scenario and drive data-driven improvements while mentoring

Qualifications

• Bachelor’s or higher in a technical field with demonstrated competencies via 6+ years (or advanced degrees with fewer years)
• Strong Python and SQL skills with large-scale data experience
• Hands-on ML and dataset curation improving downstream model performance
• Experience with Databricks or similar platforms for large-scale analytics
• Expertise in distributed compute frameworks (Ray, Spark, Beam) and cloud (AWS/GCP/Azure)
• Experience parsing complex data formats and using Pegasus-based standards for scenario data

Responsibilities

• Architect and optimize distributed data pipelines to process massive multi-sensor logs and extract safety-critical events
• Develop heuristic-based and ML-assisted algorithms to classify and describe complex scenarios
• Format scenario data using Pegasus layer standards to ensure metadata integrity
• Ingest tagged events into the observations database for ML training and validation
• Collaborate across perception, simulation, and systems engineering to define meaningful scenarios
• Mentor engineers, lead design reviews, and establish coding standards

Skills

Python

SQL

Data pipelines

ML & data curation

Databricks

Cloud platforms

Communication

Technical leadership

Education

Bachelor’s degree in CS/Robotics/EE

Master’s degree in CS/Robotics/EE

PhD in CS/Robotics/EE

Tools

Databricks

Ray

Spark

Beam

ROS/MCAP

Job description

Torc Robotics is seeking a data-focused engineer to architect distributed data pipelines for autonomous trucking data. You will extract and catalog safety-critical events from multi-sensor logs, using Pegasus standards and ML-assisted methods.

The role requires strong Python/SQL, Databricks experience, and cloud familiarity. You will collaborate with perception, simulation, and systems teams to define what constitutes a meaningful scenario and drive data-driven improvements while mentoring