Machine Learning Performance Engineer

Our mission is to build the Covariant Brain, a universal AI to give robots the ability to see, reason and act on the world around them. Bringing AI from research in the lab to the infinite variability and constant change of our customer’s real-world operations requires new ideas, approaches and techniques.Success in the real world requires a team that represents that world: diversity of backgrounds, points of view, and experiences. Our common denominator: ambitious expectations, love of learning, empathy for those around us, and a team-first mindset.

Read more about our culture at https://www.keyvalues.com/covariant .

The Covariant Brain is a Universal AI Platform that powers all robotic applications at Covariant. The Brain is a collection of state-of-the-art models, algorithms, and APIs that enable all intelligent behavior of the robot, from perception to 3d object understanding, grasp sampling, ranking, motion planning, and control. Each Application Performance Engineer will be expected to own a product family and use their understanding of the Covariant Brain to make improvements towards making robots highly autonomous. 

1. Own all performance aspects for a robotic application.2. Understand and iterate on all aspects of the Brain (models, algorithms, tooling, etc.) to resolve production failures and deliver human-level autonomy.3. Analyze robot performance for different errors, understand their root causes, and test/deploy improvements to production.4. Build tools to analyze a highly complex system of robots, models, components, and sensors to understand errors and enable more people across the org to make improvements to the system.5.

Take real-world challenges and engineer ML & robotics solutions by training, testing, tuning, iterating, and deploying new and existing models to solve production problems.6. Collaborate closely with research, SW, HW, and infrastructure teams to deliver highly reliable robotic applications. 7. Working closely with the HW team on the design of a robotic application including the gripper, vision suite, and station layout.8. Identifying throughput bottlenecks in the application and working with the SW team to pinpoint and resolve them.9. Taking experimental models from the research team, testing them to validate improvement, and deploying them to solve application problems.10. Travel to the customer site as needed to resolve issues with robots in production (not expected for more than once per quarter, if needed at all).

1. Obsession with building products that deliver value to customers through solving hard ML and robotics challenges.2. 3+ years of professional experience working with real-world software systems, AI products, or AI research. 3. Proficiency in Python and experience with tensor libraries (e.g. NumPy, PyTorch, TensorFlow).4. Working knowledge of Linux, SQL, and web (e.g. HTML, Javascript, etc.)5. A solid mathematical and statistical foundation with an understanding of how to apply ML concepts (e.g.

training, evaluation, testing, finetuning, data sampling, etc.)6. Demonstrated strong problem-solving ability: analyzing real-world problems and formulating solutions, iterating and formulating, shipping, and making an impact on products for customers.7. Clear communication and collaboration across teams: taking requests from customers, PMs, and prioritizing work across research and HW teams.

Trained, deployed, and analyzed ML models or robotics applications in production. Understanding of the state of the art in Computer Vision and Robotics literature.Experience working with complex data infra and highly concurrent SW systems.

LEARNING CONSTANTLY STRIVING FOR EMPATHYTAKING ON THE IMPOSSIBLE, TOGETHER 

Study allowanceFlexible work hoursLunch allowance and overtime meals each dayPay government insurance in full

Apply for this job