$160,800 – $193,000
Listed on Torc Robotics’s own careers site. You apply with them directly — we never stand between you and the employer.
What this role is
This role focuses on building algorithms and systems to automatically detect and categorize driving events from massive volumes of autonomous truck sensor data, turning raw logs into curated datasets that fuel development across the company's perception and simulation teams. You'll combine rule-based logic, machine learning, and geospatial reasoning to identify long-tail scenarios, then own the full pipeline from design through production monitoring on cloud-scale data systems.
Our summary, not Torc Robotics’s wording. The full posting is on their site.
Skills this role names
- Amazon CloudWatch
- Amazon Web Services (AWS)
- AWS CloudFormation
- Databricks
- Datadog
- GitHub Actions
- Grafana
- NumPy
- Pandas
- Python
- Robot Operating System (ROS)
- SciPy
- SPARK
- SQL
- Terraform
Log in to see which of these are already on your profile.
What they ask for
Required
- Bachelor's degree in Computer Science, Robotics, Electrical Engineering or related field with 6+ years of relevant experience, OR Master's degree in one of those fields with 3+ years of experience
- Algorithm design experience on real-world sensor, time-series, or geospatial data
- Strong Python skills with NumPy, pandas, SciPy; working proficiency in SQL
- Experience defining and evaluating algorithm quality against labeled or ground-truth data
- Hands-on production data systems experience: distributed compute (Spark, Ray, or Databricks), cloud platform (AWS preferred), and CI/CD
- Strong communication skills across ML, perception, and simulation teams
Nice to have
- Autonomous vehicle or robotics data experience with ROS bags, MCAP, HD maps, Frenet or lane-relative coordinates
- Familiarity with Pegasus layers or OpenSCENARIO scenario standards
- VLMs, zero-shot classification, auto-labeling pipelines, or embedding/vector search experience
- GitHub Actions, infrastructure-as-code (Terraform or CloudFormation), and observability tooling experience
- Model serving frameworks like vLLM or SGLang
- Columnar storage format familiarity (Parquet, Arrow)