At Gatik, we connect people of extraordinary talent and experience to an opportunity to create a more resilient supply chain and contribute to our environment’s sustainability.
Key Responsibilities
We are looking for talented Staff Engineers with expertise in classical and modern computer vision techniques to lead or actively contribute to the architecture, design, implementation, and delivery of a multi-modal perception system. The ideal candidate will be a software expert who has overseen a process from the R&D phase through product shipment and has a passion for leading teams and developing real-world solutions.
This role is onsite at our Mountain View, CA office.
Design and implement key components of perception system such as object detection, object tracking, and multi-sensor fusion
Build software infrastructure to enable learning algorithms to leverage large scale image/LIDAR data
Design and write highly optimized pipelines for data pre-processing, model training, data post-processing, inferencing etc.
Train perception models, evaluate their performance, investigate and fix performance bottlenecks
Develop scalable training and evaluation tools and infrastructure
Collaborate with other engineers to conduct system integration and tests
Requirements
Masters’ or Ph.D. degree in Computer Science, Electrical Engineering, Robotics or related field
7+ years of related experience
2+ years of professional experience working on Computer Vision using C++ and OpenCV
Expert knowledge of modern C++ (C++11 or later) and Python
Experience in deploying perception algorithms into real-world environments
Familiar with NVIDIA software libraries such as CUDA or TensorRT
Experience building testing and evaluation platforms
Familiarity with deep learning applied to computer vision problems
Experience working on Computer Vision problems in at least two of the following subjects: Feature detection & matching, Image Filtering, Object Tracking, 3D Estimation, 3D Reconstruction, SLAM
Proficiency in modern container technologies including Docker and Kubernetes
In-depth understanding of software performance and optimization
Strong math fundamentals and a good grasp of 3D geometry and vector math
Worked with one or more neural network frameworks, such as Tensorflow or PyTorch