Canoo Technologies Inc.

ADAS Software Engineer, Machine Learning

ID
2021-1063
Category
Engineering
Type
Full Time
Location : Location
US-OK-Tulsa
Telecommute
Yes

About Canoo

About Canoo

 Canoo’s mission is to bring EVs to Everyone and build a world-class team to deploy this sustainable mobility revolution. We have developed breakthrough electric vehicles that are reinventing the automotive landscape with pioneering technologies, award-winning designs, and a unique business model that spans all owners in the full lifecycle of the vehicle. Canoo is starting production in 2022 and is distinguished by its pioneering and experienced team of technologists, engineers, and designers. With offices around the country, the company is scaling quickly and seeking candidates who love to challenge themselves, are motivated by purpose, and possess a strong desire to get things done.

 

The “Canoo Way”

 Canoo’s success is the direct result of our disciplined application of our core operating principles and drills, which are based on three main principles: Think 80/20 (“Important versus less important”), Act 30/30 (“Reduce waste and increase output”), and Live 90/10 (“We have each other’s back”). We hire based on “MET” - Mindset, Equipment and willingness to Train - and seek individuals that take accountability and deliver results while being Humble, Hungry to succeed, and Hunting for opportunities to win. We train our team to engage with each other by modulating between their intellect (iQ) and emotional intelligence (eQ), applying Facts, Finesse, and Force when they communicate. The principles and drills of the CANOO Way have been fundamental to our success, our ability to grow, continuously improve, innovate and are at the core of our day-to-day operations.

Overview

ADAS Software Engineer develops tools and automated processes to support the accurate and timely development of machine learning algorithms for autonomous driving features. The engineer develops software for data collection, data compression, data uploading/downloading using cloud and on-prem servers. The engineer handles the training and neural network model deployment pipeline to enable machine learning scientists to efficiently deploy their algorithms.

Responsibilities

  • Develop and improve CV/ML algorithms include but not limited to object detection, object tracking, semantic segmentation
  • Participate in data collection, data cleaning, labeling, testing, and analysis for CV/ML models/algorithms
  • Develop and maintain internal database for data storage, upload, download from vehicles and develop network storage services
  • Develop scalable distributed training and evaluation system for deep learning model using docker, Kubernetes, Kubeflow etc.
  • Optimize and deploy the machine learning model in embedded system
  • Develop automation data pipeline for ADAS tasks
  • Develop an automated tool to analyze object detection inference algorithms
  • Specify and develop an automated data management tool to support data integrity in storage
  • Develop unit tests and integration tests to improve code coverage and code quality
  • Develop internal software for supporting development

Qualifications

Required 

  • 2+ years industry experience in embedded system or machining learning
  • Master's degree in a related technical field 
  • Strong written and verbal communications
  • Interested in exploring new technology and optimize the existing technology
  • Need to be on site for at least 10% of time
  • Familiarity with PyTorch or TensorFlow deep learning frameworks
  • Experience with distributed data parallelism and distributed training
  • Experience with deploy deep learning model in embedded environment
  • Experience with AWS, S3, NoSQL database
  • Familiar with C++, Python, bash

Preferred 

  • Experience with docker, Kubernetes, Kubeflow etc.
  • Experience in embedded programming for automotive
  • Experience with POSIX compliant OS
  • Expertise with machine learning tools and libraries ie. Cuda, pytorch, TensorRT
  • Experience in embedded programming for automotive

What's Cool About Working Here...

  • Meaningful, challenging work that will redefine automotive landscape and make EVs available to everyone
  • Comprehensive Health Insurance
  • Equity Compensation
  • Flexible Paid Time Off
  • Casual workplace with an unbelievable feeling of energy

Canoo is an equal opportunity-affirmative action employer and considers all qualified applicants for employment based on business needs, job requirements and individual qualifications, without regard to race, color, religion, sex, age, disability, sexual orientation, gender identity or expression, marital status, past or present military service or any other status protected by the laws or regulations in the locations where we operate. We also consider qualified applicants with criminal histories consistent with applicable federal, state and local law.

 

Any unsolicited resumes or candidate profiles submitted in response to our job posting shall be considered the property of Canoo Inc. and its subsidiaries and are not subject to payment of referral or placement fees if any such candidate is later hired by Canoo unless you have a signed written agreement in place with us which covers the applicable job posting. 

 

Canoo cares deeply about the safety of all candidates who may be asked to participate in an in-person interview. While the company remains operational, some of our positions are remote, while others require working on-site. Canoo is following the Covid-19 protocols set forth by local state and federal governance and the CDC guidelines. Candidates who are vaccinated will be asked to provide a copy of proof of vaccination upon arrival for the interview. Candidates who are not vaccinated will be asked to provide proof of a negative Covid-19 test that is no less than 48 hours old. We ask that you practice hand hygiene, social distance, and wear face coverings to reduce the risks of exposure to Covid-19. We appreciate your cooperation with our safety protocols while you explore your future with Canoo!

Options

Sorry the Share function is not working properly at this moment. Please refresh the page and try again later.
Share on your newsfeed