Senior, Software Engineer - AutoTagging

Torc Robotics is a leader in autonomous driving technology, focused on developing software for automated trucks. They are seeking a Senior Software Engineer to integrate and deploy automated event-tagging systems, build data engineering pipelines, and maintain CI/CD processes to support high-volume data processing.

Responsibilities:

• Integrate and deploy automated event-tagger into production pipelines, running and monitoring tagging tasks at scale across petabytes of vehicle log data
• Build and maintain the data engineering pipelines that organize, structure, and catalog tagged scenario data into the observations database
• Own CI/CD for the Auto Tagger pipeline using GitHub Actions, keeping deployments reliable, tested, and repeatable
• Write production grade code in Python across the pipeline, from data ingestion and transformation through model integration and deployment
• Build and operate on Databricks for large scale data processing, interactive querying, and pipeline orchestration
• Design, deploy, and scale AWS infrastructure (as code) to support high-volume, distributed processing of vehicle log pipelines — working with structured/tagged outputs and metadata
• Instrument pipelines with logging, metrics, and alerting; own on-call response for tagging job failures and data quality regressions
• Partner with ML engineers on the team to take tagging and classification models from development into a scalable, monitored production pipeline
• Ensure data quality and metadata integrity as tagged events move from raw logs into the observations database used by perception, simulation, and systems teams
• Troubleshoot and improve pipeline performance, reliability, and cost as data volume and model complexity grow

Requirements:

• BS or MS in Computer Science, Engineering, or a related field, with 5+ years of software engineering experience, including production data pipeline or ML infrastructure work
• Strong Python skills, with experience building and maintaining production data or ML pipelines
• Hands-on CI/CD experience, GitHub Actions required
• Required experience with Databricks for large scale data processing and orchestration
• Required experience with AWS, including infrastructure-as-code (Terraform or CloudFormation) for provisioning distributed processing infrastructure
• Experience processing large scale time series or unstructured datasets
• Experience with observability tooling (e.g., Datadog, Grafana, CloudWatch) for production pipeline monitoring and alerting
• Experience integrating and deploying ML models into production systems — serving, monitoring, and rollback, not just training
• Strong communication skills to work across ML, perception, and simulation teams
• Familiarity with auto-labeling pipelines, VLMs, or zero-shot classification for scenario extraction
• Experience with distributed compute frameworks such as Ray, Spark, or Daft
• Familiarity with robotics data formats (ROS bags, MCAP) and columnar storage formats (Parquet, Arrow)
• Experience with model serving frameworks such as vLLM or SGLang
• Familiarity with scenario description standards like Pegasus layers