Perception Engineer
Chef Robotics
San Francisco, CA, USA
Posted 6+ months ago
Chef Robotics is on a mission to accelerate the advent of intelligent machines in the physical world. As the rise of LLMs like ChatGPT has shown, AI has the potential to drive immense change. However, we believe AI’s biggest impact will be in the physical world, given industries like manufacturing, food, and transportation represent 90% of global GDP. We're starting with food, with a goal to put an intelligent robot in every commercial kitchen in the world. We have signed multiple multi-year contracts with various large food companies and we are growing fast. We're backed by investors like Kleiner Perkins, Construct, Bloomberg BETA and Promus Ventures. We have a great team, where you will be surrounded by talented engineers and tech leaders from companies like Cruise, Zoox, Google, Verb Surgical, Tesla, Nuro, Vicarious, Amazon Robotics, Strateos, Built Robotics, Facebook, Plenty, Yelp, and Microsoft.
Chef is looking for a Perception Engineer to help us scale our fleet of robots. You will be making a large impact on a small team, developing the next generation of our perception system that will allow our robots to reliably serve millions of meals in production environments. Ideal candidates for this role will be well-versed in the latest in deep learning, while also possessing a strong foundation in classical computer vision and state estimation.
Responsibilities & Example Projects
- Oversee the collection, labeling, and management of datasets to train and evaluate machine learning models, including working with labeling vendors to ensure high-quality data annotation and building out ML ops infrastructure.
- Employ strategies for training models with limited data, including synthetic data generation, data augmentation, transfer learning, active learning, and domain adaptation.
- Develop perception systems for object detection and segmentation utilizing both 2D and 3D image data.
- Develop systems for sensor fusion and object tracking.
- Develop scalable and productionable methods for camera calibration.
- Evaluate and select cameras and other sensors for our next-generation hardware.
- Champion engineering excellence, ensuring high-quality, well-structured, and well-tested code.
- Stay up-to-date with the latest ML and perception research and apply insights in a practical way to our System.
- Drive the development of new ideas from conception through implementation and evaluation.
- Take full ownership of perception projects, ensuring they meet and exceed performance and reliability standards.
- Be proactive in identifying potential issues and opportunities for improvement, leading efforts to develop and implement solutions.
Requirements
- BS, MS, or PhD in computer science, robotics, electrical engineering, mechanical engineering or related field.
- Practical experience shipping working perception systems.
- Minimum of 5+ years research and industry experience in machine/deep learning and computer vision.
- 5+ years experience in Python and/or C++.
- Experience with common deep learning frameworks like Tensorflow or Pytorch.
- Excellent software engineering fundamentals.
- Excellent mathematical skills, especially with probability and statistics, linear algebra, and classical machine learning.
Bonus Points
- Startup experience.
- Experience with the robotics tech stack, e.g. Linux, ROS, OpenCV, CUDA.
- Experience with SLAM, localization, calibration, state estimation, sensor fusion.
- Experience with full-stack web engineering and infrastructure.
- Experience with basic mechatronics and electronics.
- Strong publication record in top machine learning and computer vision journals.
Equal Opportunity Employer
We are an equal opportunity employer and value diversity at our company. We do not discriminate on the basis of race, religion, color, sex, gender identity and expression, sexual orientation, national origin, ancestry, citizen status, uniform service member and veteran status, marital status, age, pregnancy status, protected medical condition, genetic information, disability, or any other protected status.
Multiple studies have found that a higher percentage of women and BIPOC candidates won't apply if they don't meet every listed qualification. Chef values candidates of all backgrounds. If you find yourself excited by our mission but you don't check every box in the description, we encourage you to apply anyway!