Perception Engineer
Builds and deploys 3D perception systems for autonomous construction robots, combining cameras, LiDAR, deep-learning vision, and point-cloud geometry. The role requires Python and C++, ROS 2, computer vision, sensor fusion, and production optimization for edge hardware.
About the job
Responsibilities
- Develop and deploy 3D perception components for geometric scene understanding using depth sensors, LiDAR, and RGB cameras.
- Build ROS 2 nodes that process and interpret point clouds, depth maps, and image streams for environment modeling and task planning.
- Train and integrate deep-learning models for 3D semantic understanding, including surface analysis and object segmentation.
- Design sensor-fusion strategies combining visual, inertial, and spatial data for scene reconstruction and robot localization.
- Benchmark and optimize perception models for edge-compute platforms such as NVIDIA Jetson using TensorRT or ONNX.
- Collect and curate real and synthetic datasets; automate training pipelines and experiment tracking.
- Collaborate with manipulation, navigation, and cloud robotics teams to deliver production-ready perception stacks for autonomous operation in dynamic construction environments.
Requirements
- Strong understanding of linear algebra, probability, and geometry.
- Coursework or projects in computer vision or robotics perception.
- Proficiency in Python 3.x and C++17/20.
- Familiarity with Git and CI workflows.
- Experience with ROS 2, including
rclcpp,rclpy, custom messages, and launch configurations. - Familiarity with deep-learning vision using PyTorch or TensorFlow, including classification, detection, or segmentation.
- Hands-on experience with point-cloud processing using PCL or Open3D.
- Understanding of voxel grids, KD-trees, RANSAC, and ICP.
Nice-to-Haves
- Camera–LiDAR calibration experience.
- Experience with real-time optimization libraries such as Ceres or GTSAM.
Compensation and Benefits
- No compensation information provided.
Skills
Python, C++, Ros 2, PyTorch, TensorFlow, Pcl, Open3D, Lidar, Computer Vision, Point Clouds, TensorRT, Onnx, Ransac, Icp, Ceres
Similar jobs
ML Engineering jobs
Protege
Remote
Build the technical foundation for a new business vertical, creating reusable infrastructure and leading early customer engagements from scoping through delivery. The role requires 3+ years of engineering experience, strong Python and SQL skills, backend/data expertise, and comfort operating in ambiguity.
Adaption Labs
San Francisco, CA
Build production agent systems that plan, use tools, recover from failures, and improve over time. The role requires 5+ years of production ML or backend experience, LLM or agent deployment experience, and expertise in evaluation, tracing, observability, and agent architecture.
Adaption Labs
San Francisco, CA
Own inference-stack cost and performance by optimizing serving, caching, batching, quantization, decoding, routing, and GPU execution. The role requires 5+ years in ML systems, inference infrastructure, or performance engineering, plus strong Python and systems-language skills.
Dialpad
Bengaluru, India
Build and deploy production AI systems, including agentic workflows, RAG applications, and LLM-powered services. The role requires 5+ years of engineering experience, strong Python skills, cloud and containerization experience, and the ability to lead technical initiatives and mentor engineers.
GitLab
Bengaluru, India
Build and ship autonomous, agentic software development lifecycle capabilities, including AI agents, orchestration, and safety guardrails. The role requires senior software engineering experience, proficiency in Ruby, Go, or Python, distributed systems knowledge, and experience with AI/ML applications.