Senior, Software Engineer - AutoTagging
Core
Build and maintain production data engineering pipelines to process petabytes of vehicle log data, tag driving scenarios, and structure findings into an observations database for autonomous trucking development.
Role type
Senior Software Engineer (Data Engineering & ML Infrastructure)
Builds
Automated event-tagging pipelines, structured scenario libraries, and AWS infrastructure for autonomous vehicle data processing.
Domain
Autonomous driving / Trucking / Data Engineering
Deliverable
production ML models | product features | infrastructure
Required skills
Python, CI/CD (GitHub Actions), Databricks, AWS (Infrastructure as Code), Large-scale data processing, Observability tooling, ML model deployment
Preferred skills
Auto-labeling pipelines, VLMs, Zero-shot classification, Distributed compute (Ray, Spark), Robotics data formats (ROS, MCAP), Model serving (vLLM, SGLang)
Technologies
Python, GitHub Actions, Databricks, AWS, Terraform, CloudFormation, Datadog, Grafana, CloudWatch, Parquet, Arrow, ROS bags, MCAP, vLLM, SGLang
Responsibilities
Integrate and deploy automated event-tagger into production pipelines; Build and maintain data engineering pipelines for scenario cataloging; Own CI/CD for the Auto Tagger pipeline; Write production-grade Python code for data ingestion and model integration; Design and scale AWS infrastructure for high-volume processing; Instrument pipelines with logging, metrics, and alerting; Partner with ML engineers to deploy tagging models; Ensure data quality and metadata integrity; Troubleshoot and improve pipeline performance and cost.
Seniority
Senior, hands-on IC
