ML Runtime Optimization Engineer
Applied Intuitionover 1 year ago
Sunnyvale, CA, USAMid Level
H1B sponsor
Base Salary
$159k - $199k/yr
Responsibilities
- Drive ML performance optimization across multiple technologies for on-road and off-road ADAS and autonomous-driving stacks.
- Develop compute-usage strategies to optimize model-inference efficiency and latency on customer-selected compute boards.
- Apply model pruning and quantization to support deployment on memory-constrained platforms.
- Collaborate with ML engineers and software developers to identify and optimize efficient model architectures.
- Establish methods to profile model performance on target embedded compute platforms and identify bottlenecks during stack integration.
Requirements
- Bachelor's degree in Electrical Engineering, Computer Science, Mathematics, Physics, or a related field.
- At least 3 years of experience with ML accelerators, GPUs, CPUs, SoC architecture, and micro-architecture.
- Strong software development skills focused on embedded programming.
- Experience profiling and optimizing model performance on embedded compute platforms.
- Experience working with deep-learning frameworks such as PyTorch, JAX, and ONNX.
- Master's degree or PhD in an ML-related area is preferred.
- Experience building an ML optimization framework from scratch is preferred.
- Experience deploying ML solutions to embedded chips for real-time robotics applications is preferred.
Benefits
- Primarily in-office work five days per week, with occasional remote-work flexibility.
- Benefits may include equity, comprehensive health, dental, vision, life and disability insurance, 401(k) retirement benefits with employer match, learning and wellness stipends, and paid time off.
Tech Stack
Categories
About Applied Intuition
Applied Intuition builds software tools, infrastructure, and operating systems for developing, testing, and deploying autonomous and driver-assistance systems across automotive, trucking, defense, construction, mining, and agriculture. It sells enterprise software and services including simulation, sensor data management, HD mapping, and a vehicle OS to OEMs and government customers. Founded in 2017 and headquartered in Sunnyvale, California, it counts 18 of the top 20 global automakers and the U.S. military among its users.