Spacecraft State Estimation & Trajectory Prediction Engineer

Lodestar Space; Los Angeles (CA); On-site; USD 115,000 - 200,000; Full time

Benefits offered by this job

Equity incentives

Flexible PTO

Medical, dental & vision coverage

401(k) with company match

Based in Los Angeles

Job summary

Lodestar seeks a Graduate Software Engineer (I or II) in Los Angeles to lead state estimation and prediction for MITHRIL, Lodestar’s autonomous in-space platform. You will research and develop algorithms that fuse probabilistic estimation with machine learning to track targets, predict trajectories, and assess intent.

The role emphasizes extreme ownership culture and collaboration with perception/on-board autonomy teams to ensure robust, scalable predictions across missions.

Qualifications

• Bachelor's, Master's, or PhD in Computer Science, Aerospace, Robotics, Applied Mathematics, or related field, completed within last 24 months or before start date
• Working proficiency in C++ and Python
• Grounding in probabilistic state estimation (Kalman filters, particle filters, Bayesian inference)
• Experience with a deep learning framework (PyTorch, TensorFlow) including sequence modelling (seq2seq, RNNs, LSTMs, Transformers)
• Familiarity with trajectory modelling, multi-body dynamics, or orbital mechanics
• Ability to work through open-ended technical problems and communicate reasoning clearly

Responsibilities

• Contribute to design and implementation of core state estimation and prediction architecture for autonomous spacecraft operations
• Research and develop estimation/prediction algorithms from literature through training and deployment
• Implement, test, and benchmark estimators that track current state/trajectory of multiple targets in real time
• Build and evaluate neural models forecasting future trajectories and behavioural patterns
• Assist development of intent inference models to identify actions and rank threat levels
• Integrate models into mission simulation environments and autonomy decision systems
• Collaborate with perception/on-board autonomy teams to ensure fidelity, robustness, and scalability across missions

Skills

C++

Python

Probabilistic state estimation

Deep learning

Trajectory modelling

Education

Bachelor's/Master's/PhD in CS/Aerospace/Robotics/Applied Math

Tools

PyTorch

TensorFlow

Linux

Git

CI/CD

Docker

Kubernetes

Job description

Lodestar seeks a Graduate Software Engineer (I or II) in Los Angeles to lead state estimation and prediction for MITHRIL, Lodestar’s autonomous in-space platform. You will research and develop algorithms that fuse probabilistic estimation with machine learning to track targets, predict trajectories, and assess intent.

The role emphasizes extreme ownership culture and collaboration with perception/on-board autonomy teams to ensure robust, scalable predictions across missions.