Senior, ML Engineer - VLM
Torc Robotics2 months ago
Base Salary
$177k - $213k/yr
Responsibilities
- Design, implement, test, and deploy cloud-based pipelines that convert logged multi-sensor data into VLM/VLA training datasets.
- Develop VLM-assisted open-vocabulary detection, dense captioning, semantic enrichment, and scene or scenario description generation for large-scale auto-labeling.
- Generate language-grounded reasoning and chain-of-causation annotations aligned with ego-motion and trajectories.
- Mine rare, difficult, and high-uncertainty scenarios and curate datasets that improve downstream VLM/VLA metrics.
- Define dataset schemas, quality metrics, and validation processes, and route model failures into relabeling and retraining loops.
- Partner with end-to-end model developers to define dataset specifications and operationalize continuous dataset delivery.
- Build distributed, reproducible pipelines using columnar data formats and distributed compute.
- Lead projects, mentor engineers, run design reviews, establish coding and annotation standards, and drive cross-team alignment.
- Track advances in multimodal models, auto-labeling, and autonomous driving and translate relevant research into production data systems.
Requirements
- Bachelor’s degree in Computer Science, Robotics, Electrical Engineering, or a related technical field plus competences typically acquired through 6+ years of experience, or a related master’s degree plus competences typically acquired through 3+ years of experience.
- Strong computer vision and deep-learning experience, including model training and at least two of 2D/3D object detection, tracking, sensor fusion, semantic segmentation, BEV, or depth estimation.
- Hands-on vision-language model experience, including open-vocabulary or zero-shot recognition, dense captioning, or semantic embeddings/search applied to perception data.
- Experience building targeted datasets that improve downstream model performance and processing large-scale Parquet data.
- Experience with distributed ML and data frameworks such as PyTorch, Lightning, Ray, Spark, or equivalent tools.
- Experience with experiment tracking, model registries, MLflow or Weights & Biases, model metrics, evaluation, and quality systems.
- Strong Python development and experience with VDI, cloud-based development environments, CI systems such as GitHub Actions, and Docker.
- Preferred experience with VLM/VLA or end-to-end driving models, trajectory and action grounding, reasoning-trace datasets, foundation-model auto-labeling, high-throughput model serving, semantic retrieval, vector databases, autonomous-vehicle data standards, robotics formats, cloud orchestration, data visualization, or closed-loop/open-loop evaluation.
- Publications in top-tier computer vision, AI, or robotics venues are a bonus.
Benefits
- Competitive compensation package with bonus component and stock options.
- 100% paid medical, dental, and vision premiums for full-time employees.
- 401(k) plan with a 6% employer match.
- Flexible schedule and generous paid vacation available immediately after the start date.
- Company-wide holiday office closures.
- AD+D and life insurance.
Tech Stack
Categories
About Torc Robotics
Torc Robotics, headquartered in Blacksburg, Virginia, offers a complete autonomous software solution for the trucking/freight industry. Torc was acquired by Daimler – the largest heavy-duty truck manufacturer in North America – in August 2019. We are working together to develop highly automated trucks to improve the safety and efficiency of transporting goods. We are experts in providing autonomous vehicle solutions and we partner with other industry leaders to bring this new technology to work in the real world. Our mission is to drive the future of freight through safer roads and the efficient transport of critical goods. #TorcDriven #TorcRobotics