AI & Machine Learning Engineer

Lightspeed•Northbrook, IL

About The Position

LightSpeed Build Technologies is revolutionizing the construction industry through AI-powered robotics. Our flagship systems—BRUTE for automated wall panel manufacturing and DEX for on-site collaborative construction—are addressing the global housing crisis by delivering unprecedented speed, precision, and affordability in homebuilding. As an AI & Machine Learning Engineer, you will design, build, and deploy the intelligent systems that make LightSpeed’s construction robots smarter, faster, and more autonomous. You will develop machine learning models for computer vision, predictive analytics, autonomous decision-making, and process optimization—all deployed in real-time production environments where precision and reliability are critical. This role sits at the intersection of cutting-edge AI research and practical industrial application.

Requirements

4+ years hands-on ML engineering building and deploying production models
Deep proficiency with PyTorch or TensorFlow for model development and training
Strong computer vision experience: object detection, segmentation, depth estimation, or 3D vision
Understanding of reinforcement learning, imitation learning, or robot learning approaches
Experience optimizing ML models for edge deployment (TensorRT, ONNX, quantization)
Strong Python with experience in C++ for performance-critical components
Experience with ML infrastructure: data pipelines, experiment tracking, model serving
Proficiency with Linux, Docker, Git, and CI/CD workflows
Understanding of real-time system constraints for ML inference in production

Nice To Haves

MS or PhD in Machine Learning, Computer Science, Robotics, or related field
Experience with robotics simulation: MuJoCo, IsaacSIM, or similar
Background in manufacturing, industrial automation, or construction technology
Experience with ROS/ROS2 integration for ML-powered robotics
Published research or patents in computer vision, robot learning, or related ML
Experience with NVIDIA ecosystem: CUDA, cuDNN, TensorRT, Jetson platforms

Responsibilities

Design, train, and deploy ML models for robotic control, quality prediction, and process optimization
Develop reinforcement learning and imitation learning systems for robot task planning
Build predictive maintenance models using sensor data to anticipate equipment failures
Implement anomaly detection for real-time quality monitoring during automated assembly
Optimize model inference for edge deployment on GPU-accelerated hardware in production
Develop deep learning pipelines for object detection, segmentation, and pose estimation
Build real-time vision systems for robotic guidance, workpiece tracking, and dimensional verification
Implement 3D point cloud processing for construction material recognition
Design and train models for visual quality inspection using depth cameras and industrial imaging
Build ML data pipelines from sensor acquisition through model training and deployment
Establish data labeling, versioning, and management workflows for training datasets
Implement model monitoring, A/B testing, and continuous improvement in production
Design experiment tracking and reproducibility infrastructure (MLflow, Weights & Biases)
Integrate ML models with ROS2-based robot control for real-time inference
Optimize models for NVIDIA Jetson, industrial PCs, and edge computing platforms
Collaborate with robotics engineers on sensor selection, placement, and calibration
Support scaling ML systems across multiple production cells and sites