ML Optimization Engineer - Remote

Overview

Augmodo is at the forefront of spatial computing, where mapping connects the digital and physical worlds. As a ML Optimization Engineer, you will play the key role in our computer vision team to optimize and deploy state-of-the-art CV algorithms and pipelines. You will define and scale performance of CV and ML models on Augmodo’s edge devices. You will work at the intersection of model development and systems engineering to ensure our AI solutions are fast, scalable, and cost-effective.

In Short

• Optimize ML models for inference performance on various edge platforms (e.g. power-constrained smart badges)
• Collaborate with research and engineering teams to productionize models with a focus on latency, accuracy, and memory footprint.
• Leverage tools like TensorRT, ONNX and quantization/pruning/distillation techniques to improve efficiency.
• Benchmark model performance and guide deployment decisions.
• Stay current with advancements in model acceleration and hardware optimization.

Requirements

• Expertise in machine learning model deployment and optimization, with experience in model compression, quantization, and inference engines (e.g., TensorRT, ONNX Runtime).
• Proficiency in Python and ML frameworks like PyTorch or TensorFlow.
• Experience with CUDA, C++, or systems-level performance profiling.
• Excellent problem-solving and analytical skills.
• Strong communication and teamwork skills.
• 5 years of experience with software development in C++ and Python.
• Bachelor in Computer Science, Robotics, or a related field.

Benefits

• Master's degree or PhD in Computer Science or a related technical field.
• Experience optimizing software performance for real-time systems on embedded or robotic platforms.
• Expertise in ML model architectures, ML compilers, and runtime frameworks (e.g., TensorFlow Lite).