ML Perception Software Engineer

Applied Intuition Applied Intuition · Robotics · Sunnyvale, CA · SDS Software Engineering

ML Perception Software Engineer for autonomous vehicles/robots, focusing on building perception modules, world representations, and ML/CV algorithms for self-driving vehicles. Involves training, testing, and deploying algorithms from data collection to production.

What you'd actually do

  1. Train, modify, and create beyond-SOTA algorithms for constructing powerful world representations that can be used for perception, world modeling, and ML driven autonomy
  2. Test and evaluate your algorithms on real vehicles, owning large portions of the autonomy stack and ensuring that they provide real improvements to the driving abilities
  3. Work closely with our data, behavior, and research teams to develop the most advanced autonomy software for all domains to deploy to production for our customers

Skills

Required

  • 3+ years of experience building software components or (sub) systems that address real-world perception challenges
  • Bachelor’s in Computer Science, Electrical Engineering, Robotics, or related field
  • Strong proficiency in C++ and Python
  • Experience building machine learning models from data collection to production and deployment
  • Deep understanding of the concepts and methods behind any frameworks or libraries that they worked with
  • Interest in keeping up to date in their field, identifying trends and figuring out which new ideas are promising and which are risky.

Nice to have

  • MSc or PhD in perception or closely related field
  • Experience working in modern ML-based perception for autonomous systems
  • Deep knowledge of the current trends in computer vision including perception, reconstruction, diffusion, world models and pre training vision models.

What the JD emphasized

  • building out key capabilities of perception modules
  • building 4D world representations
  • drive the design and development of computer vision and machine learning techniques
  • building machine learning models from data collection to production and deployment
  • Deep understanding of the concepts and methods behind any frameworks or libraries that they worked with
  • Interest in keeping up to date in their field, identifying trends and figuring out which new ideas are promising and which are risky.

Other signals

  • building perception modules
  • computer vision and machine learning techniques
  • train, modify, and create beyond-SOTA algorithms
  • ML driven autonomy
  • building machine learning models from data collection to production and deployment