Software Engineer, ML Deployment and GPU Development at Scythe

We are looking for a Software Engineer focused on neural network deployment and GPU software development to join our team. The ideal candidate has experience deploying complex neural networks on hardware in challenging runtime-critical applications and leveraging GPU capabilities to accelerate workloads. This role is key to Scythe utilizing state-of-the-art machine learning models, maximizing the performance of our autonomous mower M.52, and providing reliable model deployment to our customers.

You’ll work in concert with teammates from across the company to build a rich understanding of product needs and bring those ideas to life. We expect you to be broadly experienced to be able to “see around corners”, to thrive in a fast-paced, self-managed engineering environment, and to be a collaborative, low-ego teammate who helps Scythe realize its big mission.

What you’ll do at Scythe

• Work with developers to optimize new models for in-vehicle deployment
• Build and maintain evaluation tooling to monitor the performance of offline and online models
• Work cross-functionally as a member of the Perception team
• Write clean, performant, testable code
• Leverage our extensive and growing data to train state-of-the-art ML models
• Implement and frequently ship new ML solutions onto M.52
• Perform on-vehicle testing and data collection as necessary
• Manage deployment and dependencies of perception software on-vehicle

What you know well

• Modern C and Python
• PyTorch, TensorRT, and CUDA
• Runtime performance profiling on x86, ARM and Nvidia GPUs
• Comfort iterating on complex problems and models: problem definition, data, bring-up, debugging, evaluation and deployment
• Familiarity with Linux and AWS

What you’ve maybe done

• Worked with robots or other resource-constrained platforms
• Deployed ML models to production
• Compiled ML models to multiple platforms
• Profiled and optimized ML models using CUDA
• Experience working with camera, lidar, and radar data in a robotics application

Why Scythe?

• Scythe is an early-stage but well-capitalized startup. Have a huge impact alongside an awesome team of experts shipping something the world has never before seen
• Competitive salary and equity compensation
• Fully-sponsored medical, vision, and dental insurance, including 75% funded dependent coverage
• 401(k) retirement plan (non-matching today)
• Headquarters in beautiful Longmont, CO (near Boulder, CO.) Enjoy the bounties of nature and open spaces close to home with mountain biking, hiking, skiing and more.
• Satellite offices in Austin, TX and Fort Pierce, FL 
• Flexible paid time-off and remote work to let you do your best work where and when you want (For Non-Exempt Employees, please use: 120 hours per year paid time-off)
• Highly collaborative learning culture where personal freedom, growth, and responsibility are valued
• An opportunity to have an incredible positive impact on the world

Closing

Scythe is a total compensation company, which provides employees a comprehensive salary, equity, and benefit package. However, only the minimum salary amounts are listed here. Scythe carefully considers a wide range of compensation factors, including education, years of experience, competencies and other relevant business considerations. These considerations can cause your compensation to vary along with your compensation mode preferences. The ML Engineer - Neural Net Deployment position has an expected minimum annual cash salary of $130,000. The actual pay may be higher depending on your skills, qualifications, and experience. Equity and benefits packages are NOT included in this estimate. Please note that this information is provided for those hired in Colorado only, and this role is open to candidates outside of Colorado as well.