Machine Learning Inference Engineer at Cruise
San Francisco, California, United States
🇺🇸 (Posted Jul 3 2019)
About the company
We’re Cruise, the self-driving ride-hailing service.
We are building the world’s most advanced, all-electric, self-driving cars to safely connect people to the places, things, and experiences they care about. We believe self-driving cars will help save lives, reimagine cities, redefine time in transit, and restore freedom of movement for many.
At Cruise, our engineers have opportunities to grow and develop while learning from leaders at the cutting-edge of their fields. With a culture of internal mobility, there's opportunity to thrive in a variety of disciplines. This is a place for dreamers and doers to succeed.
If you are looking to solve one of today’s most complex engineering challenges, see the results of your work in hundreds of self-driving cars, and make a positive impact in the world starting in our cities, join us.
About the role:
The AV software stack heavily relies on machine learning techniques to perform variety of tasks, each with different requirements of hardware/compute resources. Throughout the life-cycle of each machine learning model, skilled ML engineers (on both training and inference sides) work closely to prepare it for a robust, scalable, and compute/power efficient inferencing on a resource-constrained hardware accelerator. Such a close working relationship is key to fast and successful deployment of intelligent systems on the car.
Cruise is looking for a Machine Learning Inference Engineer to help us deploy highly efficient machine learning models and build the most intelligent software stack for an autonomous car.
In this position, you will work closely with machine learning engineers from different AV Engineering teams (e.g. Computer Vision, Perception), covering different machine learning algorithms across the AV software stack.
If you're interested in optimizing machine learning inference on different hardware accelerators, and want to test your skills with real-world (and practical) applications in the autonomous vehicle domain, let's chat!
Day-to-day responsibilities include:
Design and develop scalable and robust software for executing ML inference on the car
Analyze, optimize and tune performance of ML models on different hardware accelerators
Provide feedback to ML engineers about choices of operations, model architectures, and parameters
Collaborate with cross functional agile teams of AV engineers to guide the direction of inferencing and provide requirements and feature requests for hardware vendors
Closely follow industry and academic developments in the inferencing domain and provide performance guidelines and best practices for other ML engineers
Skills & requirements
You should apply for this role if you have the following qualifications:
2+ years of experience in the field of machine learning deployment
Extensive experience with ML accelerators and hardware architecture
Extensive experience with ML deployment software (e.g. TensorRT, TF Lite, etc)
Extensive experience with standard ML frameworks like Tensorflow, Caffe, Torch
You should be comfortable writing production-quality code in C++
You should be familiar with performance analysis, debugging, and optimization
MS, or higher degree, in CS/CE/EE, or equivalent in industry experience
GPU programming (e.g. CUDA, OpenCL)
Experience with ML deployment on edge/mobile devices
Experience with writing robust, safety-critical code