Space Autonomy Engineer I/II: State Estimation & Prediction

Linuxconfig; Los Angeles, Northern (CA, KY); Hybrid; USD 99,000 - 174,000; Full time

Benefits offered by this job

Meaningful equity incentives as partof

Stock options

Flexible PTO with generous paid time

401(k) retirement plan with company**

Based in Los Angeles

Job summary

Lodestar in Los Angeles is seeking a Graduate Software Engineer (I or II) focused on state estimation and prediction for our AI-enabled autonomy software MITHRIL. Lead development of estimation and prediction models to track targets, predict trajectories and assess intent.

Join an extreme ownership culture with opportunities to research, implement, and deploy advanced estimators, neural models, and integration into mission simulations across space missions.

Qualifications

• Bachelor's, Master's, or PhD in Computer Science, Aerospace, Robotics, Applied Mathematics, or a related field, completed within the last 24 months or to be completed before your start date
• Working proficiency in C++ and Python, evidenced through coursework, research, internships, or personal projects
• Grounding in probabilistic state estimation (Kalman filters, particle filters, Bayesian inference), whether from taught modules, research, or self-directed work
• Practical exposure to a deep learning framework (PyTorch, TensorFlow), including sequence modelling (seq2seq, RNNs, LSTMs, Transformers)
• Familiarity with trajectory modelling, multi-body dynamics, or orbital mechanics
• Demonstrated ability to work through open-ended technical problems and communicate your reasoning clearly

Responsibilities

• Contribute to the design and implementation of Lodestar's core state estimation and prediction architecture for autonomous spacecraft operations
• Support research into novel estimation and prediction algorithms, from literature review through training and tuning to optimisation 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 behavioural patterns of targets
• Assist in the development of 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

Skills

C++

Python

Probabilistic state estimation

Deep learning

PyTorch

TensorFlow

Trajectory modelling

Communication

Linux

Git

CI/CD

CUDA

TensorRT

Education

Bachelor/Master/PhD in CS/Aerospace/Robotics/Applied Mathematics

Tools

Docker

Kubernetes

Linux

Git

CI/CD

CUDA

TensorRT

PyTorch

TensorFlow

Job description

Lodestar in Los Angeles is seeking a Graduate Software Engineer (I or II) focused on state estimation and prediction for our AI-enabled autonomy software MITHRIL. Lead development of estimation and prediction models to track targets, predict trajectories and assess intent.

Join an extreme ownership culture with opportunities to research, implement, and deploy advanced estimators, neural models, and integration into mission simulations across space missions.