Jobs at Torc Robotics

The Office Manager oversees daily office operations, inventory, vendor relationships, SOPs, equipment troubleshooting, and facilities coordination. The role also plans workplace events, supports visitors and internal communications, manages sensitive information, and helps address office-wide operational challenges. It requires strong organization, communication, judgment, and adaptability in a fast-paced product development environment, along with occasional travel between company locations and compliance with safety requirements.

Develop and deploy machine learning models for autonomous truck behavior systems using imitation learning, reinforcement learning, and sequence modeling. Build production ML code, training pipelines, data workflows, evaluation tooling, and inference systems. Analyze model performance and failure modes, collaborate with autonomy and simulation teams, and integrate learned behavior models into simulation and validation workflows.

Reviews and audits high-definition map datasets for accuracy, completeness, and safety-critical defects. Performs quality control on geospatial data derived from LiDAR, imagery, and vehicle sensors; documents and triages issues; defines QC metrics, sampling strategies, and repeatable workflows; collaborates with mapping engineers, autonomy teams, and vendors; analyzes defect trends; maintains procedures; and supports launch readiness for new corridors and operational domains.

Lead on-truck integration and bring-up of embedded compute platforms, sensors, networking, vehicle interfaces, and software releases. Own integration readiness, root-cause investigations, validation environments, automation frameworks, system-level test strategies, and technical documentation. Partner across hardware, software, systems, and autonomy teams to improve integration quality and scalability. Mentor engineers and support architecture decisions through lab and field evidence.

Design and implement scalable mapping data-processing pipelines, APIs, and navigation systems for autonomous trucks. Translate ambiguous requirements into technical designs, build high-throughput services, collaborate with consuming engineering teams, incorporate feedback into shipped features, and debug complex software defects. The role requires programming expertise, AWS experience, strong technical communication, independent problem-solving, and familiarity with source control and agile workflows.

Own system-level simulation testing and virtual verification of autonomous driving software. Plan test campaigns, develop scenarios and test procedures, maintain scenario libraries, identify testing gaps, improve simulation toolchains, analyze results, and communicate dashboards and reports to stakeholders. Support development and integration teams through troubleshooting, fault isolation, and system-level analysis while helping improve autonomous vehicle safety and robustness.

Leads architecture and development of scalable autonomous vehicle simulation and high-fidelity truck dynamics models. Defines validation metrics, robustness testing, and verification strategies supporting safety-case claims, large-scale V&V, and reinforcement learning. Collaborates with autonomy, controls, safety, OEM, and vendor teams; performs C++ development in Linux with ROS/ROS2; investigates simulation and hardware-in-the-loop issues; drives technical direction, testing rigor, and engineer mentorship.

Lead the architecture, design, implementation, and evolution of core C++ frameworks supporting Torc’s autonomous driving stack. Drive technical direction for real-time systems, communication, state management, testing, observability, and validation. Collaborate with Behavior and Perception teams, lead architecture and code reviews, mentor engineers, resolve platform-level issues, and establish scalable software engineering standards for reliable autonomous vehicle operations.

Leads development of BEV and multi-modal perception models for autonomous trucks, combining camera, LiDAR, radar, and HD map data. Responsibilities include model architecture, large-scale distributed training, data pipelines, robustness evaluation, sensor fusion, research into foundation models, and mentoring ML engineers. The role requires deep expertise in 3D vision, autonomous systems, multi-view fusion, and production-scale machine learning.

Develop and deploy production machine learning models and sensor-fusion algorithms for autonomous-truck ego-motion estimation and localization. Build scalable PyTorch training workflows, analyze large vehicle datasets, and create robust C++ and Python production software. Define validation strategies, optimize performance under real-time constraints, make architecture decisions, and collaborate across autonomous-driving teams. Provide technical leadership through design reviews, code reviews, mentoring, and engineering best practices.

Provide on-call MLOps support for machine learning teams by triaging pipeline issues, debugging workflows, identifying root causes, and maintaining reliable model development operations. Collaborate with senior engineers to improve tooling, documentation, and processes, while communicating technical findings across teams. The role requires Python, foundational PyTorch and model pipeline experience, plus familiarity with CI/CD, monitoring, logging, and orchestration tools.

Lead cloud cost management and FinOps activities across multi-cloud environments: cost analysis, budgeting, forecasting, tagging and allocation, rate optimization, anomaly/root-cause analysis, billing data aggregation, dashboards and showback/chargeback models, and cross-functional cost governance using FinOps best practices and Lean-Agile methods.

The Director of Engineering will lead the TorcOS team in developing embedded software for autonomous driving platforms, focusing on processes, team development, and cross-functional collaboration.

Build and operate internal platform infrastructure supporting software and hardware development, testing, deployment, and release workflows for autonomous vehicles. Develop shared services for workflow orchestration, observability, remote development, authentication, and multimodal test execution. Provide incident response and internal customer support, improve reliability and scalability, troubleshoot complex issues, establish engineering standards, and mentor other engineers.

Perform operational safety analysis for autonomous heavy-truck testing, develop safety concepts, requirements, processes, procedures, metrics, and risk mitigation plans. Review designs, specifications, software, test plans, and reports for safety impacts; support incident investigations, safety cases, compliance, and readiness reviews. Collaborate across engineering, product, regulatory, service, maintenance, and fleet operations teams to ensure safe autonomous vehicle development and public-road testing.

Design, develop, and deploy production 3D and BEV perception ML models for autonomous trucks. Own end-to-end model lifecycle from data prep, training, evaluation, and deployment. Improve model robustness, performance, and generalization across sensor modalities. Integrate models with autonomy software, enhance training pipelines and tooling, analyze failures, and mentor junior engineers.

Design, implement, and optimize C/C++ drivers and integrations for sensors (PCIe, DMA, Ethernet, CAN). Maintain builds, CI/CD, and test tooling; improve real-time performance and memory usage in multi-threaded embedded Linux systems. Troubleshoot across hardware, networking, and software; integrate third-party/open-source components; document designs and mentor junior engineers.

Serve as a strategic HR partner to leaders, advising on talent management, performance, org design, employee relations, investigations, succession planning, compensation, change management, and HR analytics to align people strategies with business goals.

Build and maintain production CI/CD, build tools, and infrastructure for safety-critical AV software. Develop scalable automation, participate in on-call rotations, troubleshoot incidents, write tests, documentation, and collaborate across teams to improve release velocity and reliability.

Develop and deliver production-ready 3D and camera-based perception ML models (BEV emphasis). Own model training, evaluation, debugging, and integration into autonomy systems. Improve training pipelines, tooling, and robustness; lead small technical initiatives and mentor junior ML engineers while collaborating cross-functionally to deploy perception models at scale.