Software Engineer I or II: State Estimation & Prediction
About this role
Lodestar develops MITHRIL, a hardware-agnostic and AI-enabled autonomy software suite designed to provide protect and defend capabilities for high-value space assets in orbit. Software engineers in this team lead the creation of state estimation and prediction models that serve as the core of the flagship product. Practitioners research and build algorithms fusing probabilistic estimation with machine learning to track targets, forecast trajectories, and assess intent in real time.
Candidates joining the group operate within an extreme ownership engineering culture, collaborating closely with perception and on-board autonomy units. Successful individuals bring a solid foundation in probabilistic methods and neural sequence modeling, paired with practical coding skills in C++ and Python. This opening suits recent graduates or early-career engineers seeking to apply advanced estimation techniques to autonomous spacecraft operations.
What you will do
- Contribute to the design and implementation of core state estimation and prediction architecture for autonomous spacecraft operations.
- Support research into novel estimation and prediction algorithms, spanning literature review, training, tuning, optimization, and deployment.
- Implement, test, and benchmark classical and neural estimators that track the current state and trajectory of multiple dynamic targets in real time.
- Build and evaluate neural models that forecast future trajectories and behavioral patterns of targets.
- Assist in developing intent inference models that identify actions and dynamically rank threat levels.
- Integrate state estimation and prediction models into mission simulation environments and autonomy decision systems.
- Collaborate with cross-functional teams, including perception and on-board autonomy, to ensure prediction fidelity, robustness, and scalability across missions.
What you need
- Hold a Bachelor's, Master's, or PhD in Computer Science, Aerospace, Robotics, Applied Mathematics, or a related field, completed within the last 24 months or due for completion before the start date.
- Demonstrate working proficiency in C++ and Python through coursework, research, internships, or personal projects.
- Possess a grounding in probabilistic state estimation such as Kalman filters, particle filters, or Bayesian inference.
- Show practical exposure to a deep learning framework like PyTorch or TensorFlow, including sequence modeling experience.
- Exhibit familiarity with trajectory modeling, multi-body dynamics, or orbital mechanics.
- Prove the ability to work through open-ended technical problems and communicate reasoning clearly.
Nice to have
- Internship, industrial placement, or research assistantship in aerospace, robotics, estimation, or a related field
- A dissertation, thesis, or capstone project in state estimation, sensor fusion, or trajectory forecasting
- Experience applying sequence-to-sequence models to forecasting problems in dynamic environments
- Familiarity with sensor fusion techniques combining radar, optical, and inertial data
- Exposure to GPU acceleration using CUDA or TensorRT for neural network training and inference
Benefits
- Meaningful equity incentives as part of an employee option pool
- Flexible PTO with generous paid vacation, holidays, and sick leave
- Comprehensive medical, dental, and vision coverage
- 401(k) retirement plan with company match
Skills and tech stack
Questions candidates ask
Where is the role based?
The position is based in Los Angeles, US.
What is the compensation for this position?
The full band structure for entry level is $99,000 to $133,000 per year, while the developing level ranges from $115,000 to $174,000 per year. Individual base pay is determined on a case-by-case basis based on job-related skills, education, experience, technical capabilities, and internal equity.
What are the citizenship or residency requirements?
To conform to U.S. Government space technology export regulations under ITAR, applicants must be a U.S. citizen, lawful permanent resident, protected individual, or eligible to obtain the required authorizations from the U.S. Department of State.