Real-Time 3D Perception ML Engineer — Sensor Fusion

sensmore; Berlin (NH); On-site; USD 102,412 - 159,308; Full time

Benefits offered by this job

Stock options

Relocation assistance to Berlin

Beverages on-site

Regular social events

Job summary

sensmore is seeking a Machine Learning Engineer specializing in perception to advance real-time perception for autonomous heavy machinery. You will design 3D perception models, fuse LiDAR, radar, and camera data, and contribute to language-augmented perception inside the autonomy stack.

Ideal candidates have deep learning expertise, experience deploying models on embedded hardware, and a track record in autonomous robotics research or industry applications.

Qualifications

• Master's or PhD in Computer Science, Robotics, Electrical Engineering, or related field.
• Proficient in Python; strong experience with PyTorch.
• Deep expertise in 3D perception and sensor fusion (LiDAR–camera–radar).
• Experience deploying deep learning models in real time on embedded hardware (TensorRT, ONNX, Jetson/Orin).
• Solid understanding of machine learning, deep learning, and autonomous systems.

Responsibilities

• Design and implement deep learning models for 3D perception (object detection, segmentation, occupancy).
• Develop multimodal networks fusing LiDAR, radar, and camera data for off-highway autonomous vehicles.
• Contribute to Vision-Language-Action models integrating perception and language inputs.
• Optimize training and inference pipelines for real-time deployment on NVIDIA edge GPUs.
• Lead data initiatives for perception stack from data pipelines to model evaluation.
• Collaborate with interdisciplinary teams to integrate perception into the autonomy stack.

Skills

Python

PyTorch

3D perception

Sensor fusion

Real-time inference

Education

Master's or PhD in CS/Robotics/EE

Tools

TensorRT

ONNX

Jetson/Orin

ROS

mmdetection

Job description

sensmore is seeking a Machine Learning Engineer specializing in perception to advance real-time perception for autonomous heavy machinery. You will design 3D perception models, fuse LiDAR, radar, and camera data, and contribute to language-augmented perception inside the autonomy stack.

Ideal candidates have deep learning expertise, experience deploying models on embedded hardware, and a track record in autonomous robotics research or industry applications.