Powertrain System Modeling Engineer (multiple Levels)

Joby Aviation Joby Aviation · Robotics · San Carlos, CA · Powertrain & Electronics

Seeking an engineer to join the powertrain modeling and algorithms team. This role involves building and validating models of electric powertrain systems, applying them to assess performance, using numerical optimization for trade studies and design optimization, and developing model-based algorithms for flight applications like range prediction. Requires strong foundations in modeling, simulation, numerical optimization, data science, electric powertrains, and thermal systems.

What you'd actually do

  1. Collaboratively develop and maintain a powertrain-focused vehicle-level model, interacting closely with subject matter experts from battery, motor, inverter, thermal, and other hardware teams.
  2. Maintain and enhance the model codebase in Python and Matlab/Simulink.
  3. Use convex/NLP numerical optimization to conduct regular system or component-level performance and sensitivity analyses.
  4. Support cross-disciplinary trade studies to solve present engineering problems and guide future hardware development.

Skills

Required

  • Master of Science in Aerospace, Mechanical, or Electrical Engineering (or equivalent)
  • Differential Equations and their numerical solutions methods
  • linear algebra
  • numerical optimization (convex optimization and nonlinear programming)
  • gradient-based solvers
  • interior point methods
  • problem formulation
  • CasADI
  • IPOPT
  • SNOPT
  • cvxpy
  • modeling and analyzing of dynamical systems
  • electric powertrain systems
  • Python
  • MATLAB
  • Simulink
  • version control software (e.g. Git)
  • collaborative software projects
  • Self motivated
  • work independently
  • Strong collaborator
  • effective communicator

Nice to have

  • parallel computing
  • advanced modeling of lithium-ion batteries, electric motors, inverters
  • thermofluid systems and their modeling
  • aerospace industry
  • Advanced data science skills
  • validating complex models with various data sources
  • system and parameter identification methods
  • data-driven modeling techniques
  • linear and nonlinear system theory concepts

What the JD emphasized

  • cross-team collaborations and relationships are critical to our success