Torc Robotics

Machine Learning Engineer

• Develop and train machine learning models for learned behavior systems, including approaches such as behavior cloning, imitation learning, and reinforcement learning.
• Implement production-quality ML code to support model training, evaluation, and inference within the autonomy stack.
• Analyze model performance, identify failure modes, and propose improvements to increase robustness and generalization across scenarios.
• Contribute to model training pipelines and data workflows, curating behavior datasets from simulation, fleet logs, and on-vehicle data.
• Collaborate with simulation, validation, and autonomy engineering teams to test and evaluate learned behavior models across diverse driving environments.
• Help integrate learned behavior models into simulation and testing workflows, enabling faster iteration and more comprehensive validation.
• Support the development of tooling and infrastructure that improves experimentation speed, reproducibility, and model iteration.
• Contribute to technical discussions around model architecture and training strategies within the team.

ML Engineer II – Learned Behaviors

• Develop and train machine learning models for scene understanding, including tasks such as object detection, road and lane prediction, semantic voxel grid classification, occupancy prediction, and map understanding in bird’s-eye-view (BEV) space.
• Implement production-quality ML code to support model training, evaluation, and inference within the perception stack.
• Analyze model performance, identify failure modes, and propose improvements to increase robustness across diverse driving environments and conditions.
• Identify and interpret objects, lanes, obstacles, and weather conditions in the driving environment.
• Apply data science techniques to analyze model performance, understand data distributions, and identify corner cases.
• Contribute to multi-modal perception systems, combining signals from LiDAR, cameras, radar, and map sources into unified scene representations.
• Work with large-scale datasets from simulation, fleet logs, and on-vehicle data to curate training data and improve model performance.
• Collaborate with data, deployment, and infrastructure teams to evaluate perception models and ensure reliable performance in real-world driving scenarios.
• Help integrate perception models into the autonomy stack and testing pipelines, enabling faster experimentation and iteration.
• Contribute to tooling and infrastructure that improves training efficiency, experiment tracking, and reproducibility.
• Participate in technical discussions around model architectures, sensor fusion strategies, and training approaches within the team.

ML Engineer II – Birds Eye View

• Develop and train computer vision and deep learning models for lane detection using monocular and multimodal sensor data (cameras, LiDARs, and radars).
• Design 3D road surface models and lane geometry in bird's-eye view (BEV) space, and integrate them into Torc's autonomy pipeline.
• Analyze model performance, identify corner cases, and improve robustness across various environmental conditions and long-tail scenarios.
• Develop and optimize large-scale data processing workflows, including annotation, pseudo-labeling, and data augmentation.
• Implement adaptive training and evaluation pipelines for lane perception models.
• Own deployment work to optimize models for real-time execution on automotive-grade hardware.
• Leverage known SD and HD maps to improve the accuracy and stability of lane estimation.
• Contribute to architecture discussions, model reviews, and system-level integration efforts.

Machine Learning Engineer II – Roads and Lanes

• Développer et entraîner les modèles d’apprentissage automatique pour la compréhension de scènes, ce qui comprend des tâches comme la détection d’objet, la prédiction de route et de voie, la classification de grille par voxel sémantique, la prédiction d’occupation et la compréhension de cartes dans un espace BEV.
• Mettre en œuvre un code d’AA de qualité production afin d’appuyer l’entraînement, l’évaluation et l’inférence de modèles au sein de la pile de perception.
• Analyser le rendement de modèles, identifier les modes d’échec et proposer des améliorations afin d’augmenter la robustesse à travers différents environnements et diverses conditions de conduite.
• Identifier et interpréter les objets, les voies, les obstacles et les conditions météorologiques dans l’environnement de conduite.
• Appliquer des techniques de la science des données pour analyser le rendement des modèles, comprendre les distributions de données et identifier les « corner cases ».
• Contribuer aux systèmes de perception multimodaux, en combinant les signaux provenant des LiDARs, caméras, radars et cartes dans des représentations unifiées des scènes.
• Travailler avec des ensembles de données à grande échelle provenant des simulations, des registres de flotte et des véhicules afin d’organiser les données d’entraînement et d’améliorer le rendement des modèles.
• Collaborer avec les équipes des données, du déploiement et de l’infrastructure afin d’évaluer les modèles de perception et d’assurer un rendement fiable lors de scénarios de conduite dans le monde réel.
• Aider à intégrer les modèles de perception à la pile d’autonomie et tester les pipelines, permettant ainsi une expérimentation et une itération plus rapides.
• Contribuer aux outils et à l’infrastructure qui améliorent l’efficacité de l’entraînement, le suivi de l’expérimentation et la répétabilité.
• Participer aux discussions techniques par rapport aux architectures de modèles, aux stratégies de fusion de capteurs et aux approches d’entraînement au sein de l’équipe.

Ingénieur en apprentissage automatique, II – Modèle de scène

• Développer et entraîner des modèles d’apprentissage profond pour la perception à base de caméras, permettant à la pile d’autonomie de détecter les objets, comprendre les scènes et estimer les informations géométriques provenant de groupes visuels.
• Mettre en œuvre un code d’apprentissage automatique de qualité production pour appuyer l’entraînement, l’évaluation et l’inférence de modèles pour les systèmes de perception à base de caméra.
• Analyser le rendement de modèles à travers plusieurs scénarios de conduite, identifier les modes d’échec et améliorer la robustesse et la généralisation.
• Contribuer au développement et à l’optimisation de pipelines d’entraînement à grande échelle, y compris la préparation des ensembles de données, l’entraînement distribué et la gestion de l’expérimentation.
• Travailler étroitement avec les équipes des données pour organiser et améliorer les ensembles de données d’entraînement provenant des registres de flotte, de la simulation et des pipelines d’annotation.
• Collaborer avec des équipes pluridisciplinaires de perception, simulation et validation afin d’évaluer le rendement de modèles et contribuer à leur intégration dans la pile d’autonomie.
• Améliorer les flux de travail et outils d’expérimentation afin d’accélérer l’itération, la répétabilité et l’évaluation des modèles.
• Contribuer aux discussions sur l’architecture de modèle, les stratégies d’entraînement et le design du système de perception.

Ingénieur en apprentissage automatique, II

• Develop and train machine learning models for learned behavior systems, including approaches such as behavior cloning, imitation learning, and reinforcement learning.
• Implement production-quality ML code to support model training, evaluation, and inference within the autonomy stack.
• Analyze model performance, identify failure modes, and propose improvements to increase robustness and generalization across different scenarios.
• Contribute to model training pipelines and data workflows, organizing behavior datasets from simulation, fleet logs, and vehicle data.
• Collaborate with simulation, validation, and autonomy engineering teams to test and evaluate learned behavior models across various driving environments.
• Help integrate learned behavior models into simulation and testing workflows, enabling faster iteration and more comprehensive validation.
• Support the development of tools and infrastructure that improve experiment velocity, reproducibility, and model iteration.
• Contribute to technical discussions regarding model architectures and training strategies within the team.

Machine Learning Engineer II

Full-stack Engineer

• Create robust and resilient pipelines to process massive daily volumes of data created by vehicle fleets
• Build and support scalable pipelines as part of Torc’s Data Factory to deliver data for ML training at scale
• Scale Torc’s data lake through a distributed storage system, data crawling and discovery
• Promote and protect the integrity of data through validation, versioning, data provenance, and governance
• Support the expansion of Torc’s data lake through acquisition of additional data sets from internal and external sources
• Assist in the development and delivery of cloud-based solutions
• Collaborate with teams specializing in perception, planning, control, mapping and vehicle testing to develop solutions that support product delivery
• Support the implementation of emerging cloud-based capabilities that can extend our technology stack and improve our ability to build, deploy and test safety-critical software for self-driving vehicles
• Participate in the team’s on-call rotation to support our deployed systems during business hours

Senior Software Engineer – Data Ingestion

• Design and implement scalable sensor calibration pipelines in Python and C++, leveraging OpenCV, ROS, and linear algebra libraries for real-time and offline calibration.
• Develop tools to perform and automate camera intrinsic calibration, Lidar-to-camera, and IMU-to-camera extrinsic calibration.
• Apply mathematical rigor using Lie groups, quaternions, and 3D transformations to support accurate calibration and registration.
• Build and maintain simulation tools and data pipelines for sensor modeling and calibration validation.
• Work closely with perception, simulation, and platform teams to ensure calibration accuracy across hardware configurations and software versions.
• Utilize Docker, Bazel, and Git to develop reproducible, containerized calibration workflows integrated into CI/CD pipelines.
• Debug sensor alignment issues in vehicle logs and simulation using ROS tools, rviz, and custom visualizers.

Senior Software Engineer – Sensor Calibration

Technical Product Manager

• As a Technical Product Manager leading Metrics, Mission Management, Product Safety Assurance, and Regulatory workstreams, you will serve as a conduit between the needs of Regulatory, Engineering, Safety, and other critical functions.
• Identify and prioritize the needs for these workstreams and work with other TPMs and engineering leaders to ensure timely design and implementation into E/E systems as well as operational safety.
• Represent these areas to build cross-functional plans, define and verify acceptance criteria, drive alignment, and deliver these workstream's Outcomes on the Technology Roadmap to enable critical product milestones.
• Vigilantly work to reconcile gaps in timelines, focus leadership attention, and proactively address dependencies, risks, and change management. You will leverage this roadmap, partnering with other TPMs and engineering leadership to inform the short and long-term priorities of these workstreams to support engineering in advancing our company’s milestones.
• Apply best practices in program management and engineering expertise to report status to leadership, initiate escalations, drive timely execution on the Technology Roadmap including its dependencies, risks, and changes.

Senior Technical Product Manager – Product Safety Assurance

Account Manager

• Represent the TORC at community events, town halls, business association meetings, chamber of commerce gatherings, and local conferences.
• Develop and maintain strong relationships with state and local community leaders, workforce development organizations, first responders, academic institutions, and non-profit groups.
• Coordinate informational sessions, facility tours, technology demos, and educational programs to increase community awareness and understanding of autonomous trucking.
• Attend meetings with state and local government officials, transportation agencies, public safety departments, and regulatory stakeholders.
• Conduct policy research to support development of policy briefs, memos, and summaries.
• Support legislative tracking activities, monitoring, and analysis.
• Manage a calendar of outreach activities and proactively identify partnership opportunities.
• Work cross-functionally with policy, operations, communications, and safety teams to ensure alignment across outreach initiatives.

Government Relations Manager

• Develop and Optimize Computer Vision Algorithms
• Contribute to BEV and 3D Perception Architectures
• Data Management and Processing
• Model Deployment and Optimization
• Cross-functional Collaboration
• Research and Innovation
• Leadership

Senior ML Engineer – Unstructured Environments

Engineer

• Evaluate simulation-based validation strategies to ensure coverage of safety-critical behaviors across the ODD
• Assess scenario libraries and simulation inputs to identify gaps, redundancies, and risk exposure
• Analyze simulation results and validation data to understand system behavior, robustness, and failure modes
• Partner with simulation and autonomy teams to guide scenario selection and prioritization
• Correlate simulation evidence with real-world driving data to assess fidelity and coverage
• Provide high-level validation insights that inform safety cases, readiness reviews, and deployment decisions
• Recommend improvements to simulation workflows, metrics, and validation methodologies
• Serve as a senior technical voice on validation strategy, mentoring engineers and influencing best practices

Senior Simulation and Scenario Validation Engineer

Data Entry

• As a Data Annotator, you will work with 2D images and 3D sensor data to help AI systems recognize and understand their environment.
• Label objects using specialized tools to create 2D bounding boxes, 3D cuboids, and other shapes representing vehicles, road elements, obstacles, and more.
• Review pre-labeled data to ensure it complies with detailed guidelines.
• Accept, reject, or correct annotations using our software.
• Provide clear notes when corrections are required.
• Learn and progressively master our internal tools.
• Your work directly contributes to the development of safer autonomous vehicle technologies by ensuring AI models are trained on accurate, high-quality data.

Data Annotator

Security Engineer

• Develop and maintain a comprehensive product cybersecurity architecture for our product ecosystem, ensuring alignment with industry standards and business objectives.
• Stay well-informed of emerging cybersecurity threats and technologies; continuously updating our cybersecurity strategies and solutions accordingly.
• Oversee and evaluate the implementation of cybersecurity controls, including but not limited to, encryption, access controls, network security, and secure coding practices.
• Collaborate with product development teams to incorporate cybersecurity into the design and development lifecycle of products.
• Liaise with external cybersecurity vendors and partners, managing relationships, and ensuring the effective integration of third-party security solutions.
• Responsible for career development and performance management of the team.
• Document, maintain, and lead the implementation of key activities in the cybersecurity management system.
• Conduct, with a cross-functional team, a thorough threat analysis and risk assessment for existing and new products; identifying potential vulnerabilities and proposing mitigation strategies.
• Complete the evidence to support the safety case claims for product cybersecurity.
• Ensure compliance with relevant industry, regulatory, and organizational cybersecurity standards and policies.
• Represent Torc at external standards and industry bodies and communicate our product cybersecurity approach.
• Prepare and present reports on cybersecurity architecture, risk assessments, and mitigation strategies to senior management and relevant stakeholders.
• Participate in and support product cybersecurity incident response and forensic activities.
• Coordinate and share cybersecurity information, risk assessments, and incident updates with IT and Enterprise Cybersecurity teams to ensure consistent alignment of product cybersecurity practices with enterprise-wide standards and response protocols.