ML Runtime Optimization Engineer - Lead

About Applied IntuitionApplied Intuition is a vehicle software supplier that accelerates the adoption of safe and intelligent machines worldwide. Founded in 2017, Applied Intuition delivers the AI-powered ADAS/AD toolchain, vehicle platform, and autonomy stack to help customers shorten time to market, build high-quality systems, and create next-generation consumer experiences. 18 of the top 20 global automakers trust Applied Intuition’s solutions to drive the production of modern vehicles. Applied Intuition serves the automotive, trucking, construction, mining, agriculture, and defense industries and is headquartered in Mountain View, CA, with offices in Ann Arbor and Detroit, MI, Washington, D.C., Stuttgart, Munich, Stockholm, Seoul, and Tokyo. Learn more at appliedintuition.com.Please note that we are an in-office company, which means the expectation is that you would come in to your Applied Intuition office 5 days a week.About the roleWe are looking for a lead software engineer with deep experience in optimizing ML models and deploying them on production-grade embedded runtime environments. You’ll work across the entire ML framework stack (e.g. PyTorch, JAX, ONNX, TensorRT, CUDA, XLA, Triton).At Applied Intuition, you will:Drive ML performance optimization on multiple technologies for on-road and off-road ADAS / AD stacks targeting deployment on a variety of embedded compute platforms Bring technical leadership to the ML model performance optimization teamDevelop compute usage strategies to optimize efficiency and latency of model inference for compute boards selected by our customersWork on model pruning and quantization, and support deployment on memory constrained platformsCollaborate closely with ML engineers and software developers on technical efforts to find and optimize efficient model architecture solutionsSet up methodologies to profile the model performance on target embedded compute platforms and identify performance bottlenecks as part of stack integration We're looking for someone who has:Bachelors in Electrical Engineering or Computer Science, OR B.Sc. in Computer Science, Mathematics, Physics or a related field5+ years of experience with ML accelerators, GPU, CPU, SoC architecture and micro-architectureStrong software development skills with the focus on high-performance computingExperience profiling and optimizing model performance on embedded compute platformsExperience in working with deep learning frameworks (e.g., PyTorch, JAX, ONNX, etc.)Nice to have:M.Sc or PhD in a ML related areaBuilt a ML compiler or optimization framework from scratch beforeDeployed ML solutions to embedded chips for real time robotics applicationsCompensation at Applied Intuition for eligible roles includes base salary, equity, and benefits. Base salary is a single component of the total compensation package, which may also include equity in the form of options and/or restricted stock units, comprehensive health, dental, vision, life and disability insurance coverage, 401k retirement benefits with employer match, learning and wellness stipends, and paid time off. Note that benefits are subject to change and may vary based on jurisdiction of employment.Applied Intuition pay ranges reflect the minimum and maximum intended target base salary for new hire salaries for the position. The actual base salary offered to a successful candidate will additionally be influenced by a variety of factors including experience, credentials & certifications, educational attainment, skill level requirements, interview performance, and the level and scope of the position.Please reference the job posting’s subtitle for where this position will be located. For pay transparency purposes, the base salary range for this full-time position in the location listed is: $199,295 - $264,500 USD annually. Don’t meet every single requirement? If you’re excited about this role but your past experience doesn’t align perfectly with every qualification in the job description, we encourage you to apply anyway. You may be just the right candidate for this or other roles.Applicants will be required to be fully vaccinated against COVID-19 upon commencing employment. Reasonable accommodations will be considered on a case-by-case basis for exemptions to this requirement in accordance with applicable federal and state law. Applicants should be aware that for external-facing roles that involve close contact with Company employees or other third parties on the Company's premises, accommodations that involve remaining unvaccinated against COVID-19 may not be deemed reasonable. The Company will engage in the interactive process on an individualized basis taking into account the particular position.Applied Intuition is an equal opportunity employer and federal contractor or subcontractor. Consequently, the parties agree that, as applicable, they will abide by the requirements of 41 CFR 60-1.4(a), 41 CFR 60-300.5(a) and 41 CFR 60-741.5(a) and that these laws are incorporated herein by reference. These regulations prohibit discrimination against qualified individuals based on their status as protected veterans or individuals with disabilities, and prohibit discrimination against all individuals based on their race, color, religion, sex, sexual orientation, gender identity or national origin. These regulations require that covered prime contractors and subcontractors take affirmative action to employ and advance in employment individuals without regard to race, color, religion, sex, sexual orientation, gender identity, national origin, protected veteran status or disability. The parties also agree that, as applicable, they will abide by the requirements of Executive Order 13496 (29 CFR Part 471, Appendix A to Subpart A), relating to the notice of employee rights under federal labor laws.