Jobs at Torc Robotics

• Own and evolve the technical architecture for scalable vehicle modeling and simulation — extensible across vehicle types, sensor platforms, and fleet variability as Torc's autonomy program grows.
• Develop and own high-fidelity truck and vehicle dynamics models (longitudinal, lateral, and transient behavior) spanning nominal, off-nominal, and failure-mode simulation domains.

Job Duties: Lead and ensure the technical excellence of solutions delivered by the Metrics for Release and Hardware-in-the-Loop (HiL) groups and guide their integration within Torc's self-driving product portfolio. Architect scalable platform systems for validating autonomous driving software, in...

• Lead the architecture, design, implementation, and evolution of core frameworks that serve as the foundation for Torc's autonomous driving stack, including state management, inter-component communication, abstraction layers, and common utilities used across all software systems.
• Drive the technical direction for real-time C++ architectural components and patterns responsib...

• Architect, build, and own backend services and data pipelines that power the map validation and simulation pipelines for the autonomous trucking platform.
• Provide technical leadership to the annotation platform building scalable web-based annotation tooling including cuboid and polygon editing, cross-frame interpolation and track propagation, attribute editing, and review-first (accept/reject) workflows.

• Scenario Mining at Scale: Architect and optimize distributed data pipelines to process massive multi-sensor logs (camera, LiDAR, radar, kinematics), automatically extracting and cataloging safety-critical and long-tail driving events.
• Advanced Event Tagging: Develop and tune both heuristic-based and ML-assisted algorithms (inclu...

• Lead BEV model development: define and execute the technical roadmap for BEV-based perception models across multiple tasks (e.g., detection, segmentation, road topology, and scene understanding).
• Design advanced multi-modal architectures that fuse heterogeneous sensor data (camera, LiDAR, radar, HD maps) into unified spatial representations.

• Create robust and resilient pipelines to process massive daily volumes of data created by vehicle fleets and simulation environments
• Build and support scalable pipelines as part of Torc’s Data Factory to deliver data for ML training at scale

• Design, build, and own the data models that serve as the single source of truth for BI reporting — structuring tables, views, and semantic layers so metrics are defined once and used consistently across all dashboards and tools.
• Design, build, and maintain ETL/ELT pipelines that feed those models, ensuring data is accurate...

• Design, develop, and deploy production ML models for ego-motion estimation and localization, including learned pose estimation, sensor extrinsic calibration, map matching, and sensor fusion using camera, LiDAR, radar, and other vehicle sensors.
• Develop scalable training and evaluation workflows using PyTorch, distributed training infrastr...

• Lead, grow, and set technical direction for the Offline Perception team — hiring, mentoring, and managing the performance and career growth of engineers and ML engineers.
• Own the roadmap for offline perception model development and evaluation, from curated datasets through training, benchmarking, and delivery to downstream consumers.

• Provide on-call MLOps support for model development teams, triaging and resolving pipeline issues as they arise.
• Assist in debugging model development workflows and identifying root causes across the ML stack.

• Design and construct platform infrastructure spanning build, test, deployment, and release workflows across software and hardware environments.
• Periodic on‑call shifts during business hours focused on incident response and operational support for team‑owned services.

• Architect and implement model conversion and compilation pipelines using tools such as ONNX, TensorRT, and torch.compile for deployment on edge devices (e.g., NVIDIA Orin).
• Maintain and evolve the model release registry, ensuring traceability and reproducibility across model versions and target platforms.

• Deliver through your team as well as collaborate across teams to deliver high quality system releases for Torc’s autonomous driving product line.
• Maintain a rapid engineering development schedule for self-driving software stack with consistent and managed releases, both internal and external to Torc.

• Design, develop, and maintain the TypeScript/React web application for 2D and 3D annotation, including cuboid and polygon editing, cross-frame interpolation and track propagation, attribute editing, and review-first (accept/reject) workflows.
• Build high-performance point cloud and image rendering with three.js/WebGL: octree/LOD-based st...

• Build technology solutions, analyze requirements, and seek guidance from your manager and peers on scope and objectives.
• Contribute to design discussions, proposing solutions and creating diagrams and design documents for clarity.

• Own the design, implementation, and deployment of offline 3D reconstruction, lane line detection, and automatic mapping/map creation systems that generate high-quality annotations on Cloud Services from logged sensor data (Cameras, Lidars, Radars, GPS/IMU).
• Lead lane line network reconstruction efforts, rebuilding topologically correct lane line graph...

• Design, develop, and improve machine learning models supporting Torc's perception systems.
• Own model development and delivery for well-defined perception problem areas, from data preparation and training through evaluation and integration.

• 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.

• Design, implement, test and deploy tooling and pipelines for internal quality control and issue identification of pseudo-labeled data, ensuring annotations meet the bar required by downstream model training.
• Provide statistical support and report on pseudo-label quality, coverage, and pipeline health t...