- Focus on the mission
- Demonstrate grit
- Never stop learning
- Pursue excellence
Job description
Quilter is hiring a Senior to Staff level Reinforcement Learning (RL) Engineer to join our team.
Although Quilter's automated circuit board design software is already the most sophisticated in the world, it is in many ways still in its infancy. Today, Quilter's completes the several intermediate steps in its circuit board design workflow using a mix of traditional executable software and RL agents trained in specific contexts to complete narrow tasks at a superhuman level. In the long term, our goal is to design boards end-to-end with RL-trained agents.
We're looking for a talented RL Engineer who has significant experience designing, setting up, training, and successfully applying RL models and outputs in a commercial context. We need someone who can act as an extremely capable senior owner who will own and solve some of the most complex and impactful challenges on our technology roadmap. This is an opportunity to be a foundational contributor to an extremely exciting commercial application of reinforcement learning, and to work with a focused and dedicated team of experienced ML/AI researchers and engineers.Requirements
- M.Sc. or Ph.D. (preferable) focusing on one or more of the following areas: Reinforcement Learning, Robotics, Computer Science, Artificial Intelligence, Mathematics, or a closely related field
- Demonstrated research publications in any of the major conferences
- Proficient with Python and C++.
- Proficient with PyTorch or TensorFlow.
What you'll do
- Develop reinforcement learning or imitation learning algorithms to tackle various parts of the board design pipeline
- Research new models and training algorithms that push the boundaries of complexity that our algorithms can currently tackle
- Apply modern techniques found in recent literature on applications of reinforcement learning to limited-data domains such as Robotics trained without simulation data
- Run Physics simulations to compute rewards for your agent to develop policies that optimize for ideal Electromagnetic and Thermal properties of PCBs
- Build production-grade environment that model the problem of PCB design for your agents to explore and exploit
- Validate your policies against our internal gauntlet of design benchmarks
What we value
- You are a jack of all trades - equally happy implementing a recent research paper, writing production grade environments and wrangling the infrastructure required for training
- You have significant experience with applying reinforcement learning in advanced research or production contexts (such as Robotics, Self-driving cars, Gaming)
- You have trained agents that have had to generalize across a wide set of environments or a wide set of control options
Please note: We are an equal opportunity employer and currently a remote-only company. At this time, we are focused on hiring primarily within the US, with occasional exception to accommodate exceptional talent.What we offer:
- Interesting and challenging work
- Competitive salary and equity benefits
- Remote work with no commute
- Health, dental, and vision insurance
- Regular team events and offsites (~2x / year)
- Unlimited paid time off
- Paid parental leave
Want to learn more about Quilter, our vision, and our investors? Visit our About page and visit our Blog.Quilter focuses on Hardware, Machine Learning, Electronics, and Hardware + Software. Their company has offices in Los Angeles, San Francisco, and San Diego. They have a small team that's between 11-50 employees.
You can view their website at
- Interesting and challenging work
Senior to Staff Reinforcement Learning - Los Angeles, United States - Quilter
Description
About Quilter
At Quilter, we are helping electrical engineers save time and accomplish more by automating the tedious and time-consuming task of designing circuit boards. Our team is composed of experts in electrical engineering, ML/AI, and software development leveraging (and inventing) novel techniques to solve the decades-old problem of automating circuit board design.
Created in 2021, Quilter has been fully remote from the start with team members distributed throughout the US and an unofficial "headquarters" in Los Angeles, CA. No matter where we come from, we're united by a common vision for the future and a core set of values we think will get us there: