Staff, Machine Learning Engineer - BEV/Multi-Modal Perception

torcrobotics; Stati Uniti; Ibrido; USD 216.000 - 259.000; Tempo pieno

Vantaggi offerti da questo lavoro

Hybrid work in US

Remote options across the UnitedStates

Stock options

Bonus opportunity

401(k) with match

Descrizione del lavoro

TORC Robotics is seeking a Staff Machine Learning Engineer to lead BEV-based perception and multi-modal fusion for autonomous trucking. You will design cutting-edge models that fuse camera, LiDAR, radar, and maps into rich 3D representations.

The role emphasizes technical leadership, model innovation, and mature experimentation pipelines, with hybrid work options and strong compensation. You will mentor engineers and drive impactful research through deployment-ready systems.

Competenze

• 10+ years of deep learning for perception, 3D vision, or autonomous systems.
• MS or PhD in CS/EE/Robotics or equivalent practical experience.
• Expertise in BEV modeling and multi-view fusion.
• Strong background in camera-LiDAR fusion and multi-modal data.

Mansioni

• Define the technical roadmap for BEV-based perception models.
• Architect multi-modal networks for Camera, LiDAR, Radar, and HD map inputs.
• Build perception models using BEV transformers and voxel-based encoders.
• Own large-scale training pipelines: data sampling, augmentation, distributed training, hyperparameter tuning.
• Improve robustness for low visibility and occlusions.

Conoscenze

BEV modeling

3D scene understanding

multi-view fusion

Python

PyTorch

TensorFlow

distributed training

data pipelines

mentoring

ML model innovation

leading teams

Formazione

MS/PhD in CS/EE/Robotics or equivalent

Strumenti

Ray

Descrizione del lavoro

Role overview

A Staff Machine Learning Engineer position focused on Bird's-Eye View (BEV) and multi-modal perception for autonomous trucking. The role centers on designing and advancing perception models that fuse heterogeneous sensor data into rich spatial representations of the driving environment. It is a technical leadership track concentrated on model innovation and maturity rather than downstream feature integration.

Responsibilities

• Define and execute the technical roadmap for BEV-based perception models spanning detection, segmentation, road topology, and scene understanding.
• Architect multi-modal networks that unify camera, LiDAR, radar, and HD map inputs into cohesive spatial representations.
• Build foundational perception models using BEV transformers, voxel-based encoders, or implicit scene representations.
• Own large-scale training pipelines including data sampling, augmentation, distributed training, and hyperparameter optimization.
• Improve model robustness and generalization across long-tail conditions such as low visibility, occlusions, and rare scene configurations.
• Establish evaluation frameworks for geometric accuracy, temporal stability, and cross-domain transfer performance.
• Collaborate with sensor calibration, mapping, and fusion teams to align perception model interfaces.
• Mentor ML engineers on experimentation, code quality, and model validation practices.
• Track relevant research, including self-supervised learning, large-scale pretraining, and foundation models for 3D perception.

Requirements

• 10+ years of experience in deep learning for perception, 3D vision, and/or autonomous systems.
• M.S. or Ph.D. in Computer Science, Electrical Engineering, Robotics, or a related field, or equivalent practical experience.
• Demonstrated expertise in BEV modeling, 3D scene understanding, and multi-view fusion.
• Strong background in multi-modal sensor fusion, particularly camera and LiDAR integration.
• Proficiency in Python and deep learning frameworks such as PyTorch or TensorFlow.
• Experience with large-scale data pipelines, distributed training, and experiment management systems.
• Track record of leading ML model innovation and mentoring technical teams.

Nice to have

• Production experience in autonomous driving or robotics perception.
• Familiarity with MLOps tooling and infrastructure such as Ray.
• Hands-on expertise with BEV-based architectures, LiDAR-vision fusion, or spatial-temporal modeling.
• Understanding of 3D labeling, calibration, and sensor simulation pipelines.
• Publications or open-source contributions at top venues such as CVPR, ICCV, NeurIPS, ICRA, or CoRL.
• Awareness of deployment constraints including latency, memory, and accuracy tradeoffs.

Benefits and work setup

• Hybrid work available in Ann Arbor, MI, with remote options across the United States.
• Compensation range of $215,500-$258,600 USD, plus bonus and stock options.
• 100% employer-paid medical, dental, and vision premiums for full-time staff.
• 401(k) plan with a 6% employer match.
• Flexible scheduling, generous paid vacation available from the start date, and company-wide holiday closures.
• AD+D and life insurance coverage.