Senior, Software Engineer - AutoTagging
Torc Robotics2 months ago
Base Salary
$161k - $193k/yr
Responsibilities
- Integrate and deploy automated event taggers into production pipelines operating across petabytes of vehicle log data.
- Build and maintain data engineering pipelines that organize and catalog tagged scenario data in the observations database.
- Own CI/CD for the AutoTagger pipeline using GitHub Actions.
- Write production-grade Python for data ingestion, transformation, model integration, and deployment.
- Build and operate Databricks workloads for large-scale processing, querying, and orchestration.
- Design, deploy, and scale AWS infrastructure as code for distributed vehicle-log processing.
- Implement logging, metrics, and alerting and provide on-call response for job failures and data-quality regressions.
- Partner with ML engineers to move tagging and classification models into scalable, monitored production pipelines.
- Ensure data quality and metadata integrity as tagged events move from raw logs to the observations database.
- Troubleshoot and improve pipeline performance, reliability, and cost as data volume and model complexity increase.
Requirements
- BS or MS in Computer Science, Engineering, or a related field.
- 5+ years of software engineering experience, including production data pipeline or ML infrastructure work.
- Strong Python skills and experience building and maintaining production data or ML pipelines.
- Hands-on CI/CD experience with GitHub Actions.
- Experience with Databricks for large-scale data processing and orchestration.
- Experience with AWS and infrastructure as code using Terraform or CloudFormation.
- Experience processing large-scale time-series or unstructured datasets.
- Experience with observability tools such as Datadog, Grafana, or CloudWatch.
- Experience integrating and deploying ML models into production systems, including serving, monitoring, and rollback.
- Strong communication skills for collaboration across ML, perception, and simulation teams.
- Bonus: familiarity with auto-labeling pipelines, VLMs, or zero-shot classification.
- Bonus: experience with Ray, Spark, or Daft.
- Bonus: familiarity with ROS bags, MCAP, Parquet, and Arrow.
- Bonus: experience with vLLM or SGLang.
- Bonus: familiarity with Pegasus layers.
Benefits
- 100% paid medical, dental, and vision premiums for full-time employees.
- 401(k) plan with a 6% employer match.
- Flexible schedule and generous paid vacation available immediately after start date.
- Company-wide holiday office closures.
- AD&D and life insurance.
- Bonus component and stock options are included in the compensation package.
Tech Stack
Categories
About Torc Robotics
Torc Robotics develops autonomous driving software for heavy-duty trucks, offering a full self-driving stack, mapping, and perception for freight carriers and OEMs. Founded in 2005 and headquartered in Blacksburg, Virginia, it was acquired by Daimler Truck in 2019. As a subsidiary, Torc focuses on commercializing Level 4 trucking with its parent’s vehicle platforms and industry partnerships in North American freight transport.