Skip to main content

Lodestar

Software Engineer I or II: State Estimation & Prediction

Los Angeles, US$99k–$133kmidAdded 4 days ago

About this role

Lodestar is seeking a Software Engineer I or II to develop state estimation and prediction algorithms for autonomous spacecraft operations. You'll research and implement probabilistic estimation and machine learning models to track targets, predict trajectories, and assess threat intent for their flagship MITHRIL autonomy software.

What you'll do

  • Design and implement core state estimation and prediction architecture for autonomous spacecraft
  • Research and develop novel algorithms combining probabilistic estimation with machine learning
  • Implement and benchmark classical and neural estimators for real-time target tracking
  • Build and evaluate neural models for trajectory forecasting and behavioral prediction
  • Develop intent inference models to identify threat actions and rank threat levels
  • Integrate prediction models into simulation environments and autonomy decision systems

What they're looking for

  • C++ and Python programming
  • Probabilistic state estimation (Kalman filters, particle filters, Bayesian inference)
  • Deep learning frameworks (PyTorch or TensorFlow)
  • Sequence modeling (seq2seq, RNNs, LSTMs, Transformers)
  • Trajectory modeling and orbital mechanics
  • Sensor fusion techniques
  • GPU acceleration (CUDA, TensorRT)
  • Linux, Git, and CI/CD pipelines
Apply with Autofill

Opens the application — the Jobs AI extension fills it for you. Set up autofill

Opens the official application on the employer’s site. No login required.

Lodestar

Lodestar develops MITHRIL, an AI-powered autonomy suite for autonomous spacecraft operations that combines state estimation, perception, and real-time decision-making capabilities. The company is hiring Software Engineers specializing in state estimation, perception algorithms, and on-board autonomy to build advanced systems for space target detection, trajectory prediction, and autonomous mission execution.

View all jobs at Lodestar

Likely interview questions

  • Walk us through a state estimation problem you've solved—what algorithm did you choose and why?
  • How would you approach building a neural network to predict spacecraft trajectories given noisy sensor data?
Unlock all 7 questions free — and practice them live →