Job Description

Perceptive Space Systems is building a decision intelligence platform to help satellite and launch operators navigate the growing risks posed by space weather and the space environment. We work at the intersection of aerospace, AI, and real-time systems, combining cutting-edge modeling, sensor fusion, and autonomy to improve operational resilience in orbit. Read more here.

Join us at the frontier of space technology and AI

You will build the foundational technology required for satellites, launch vehicles, and human missions to operate safely and efficiently in the harsh space environment


As part of our small, high-velocity team, you'll work at the intersection of aerospace, autonomy, and applied AI, solving real-world challenges with immediate mission impact.


This

role is ideal

for entrepreneurial engineers who want to build from first principles, move fast, and own core systems end-to-end and who take initiative, thrive in ambiguity, and be part of a demanding startup environment.

What You'll Do

Build and evaluate machine learning models for time series forecasting and spatio-temporal dynamics Design experiments to assess model generalization, uncertainty, and relevance to physical systems Integrate domain knowledge, external signals, or prior constraints to improve model performance Optimize model performance through feature engineering, architecture tuning, and validation strategies Collaborate with aerospace engineers, software engineers, and domain experts to deploy ML systems in production Stay up to date with developments in ML for dynamic systems, forecasting, and scientific ML

Requirements

4+ years of industry experience following a Master's or PhD in Physics, Electrical Engineering, Applied Math, or a related field Experience in fast-paced, high-ownership ML roles within a startup or a fast-moving, demanding startup-like environment. Proficient in Python and experienced with deep learning frameworks such as PyTorch or TensorFlow Experienced with tools and frameworks like MLflow, Ray, Dask, and Numba Strong background in modeling temporal or sequential data (e.g., time series forecasting, state-space models, signal processing) Comfortable working with multidimensional datasets and integrating domain context into modeling Strong general foundations in software engineering, including coding standards, code reviews, source control (e.g., Git), build processes, and testing Experience deploying ML solutions onto cloud platforms (e.g., AWS, GCP, Azure) Track record of contributing to the successful delivery of production-ready ML models Able to explain model behavior, assumptions, and limitations clearly to both technical and non-technical stakeholders Excellent communication and collaboration skills; able to work effectively across disciplines

Bonus If You Have

Experience working in early-stage or cross-disciplinary R&D teams Experience working on scientific modeling, simulation data, or systems governed by physics or control principles Familiarity with techniques for uncertainty quantification and physics-informed ML A track record of publications or contributions to open-source ML libraries Proficient in C/C++ and Java

Additional Requirements

Due to contract requirements, applicants

must be Canadian citizens or permanent residents

. The role is fully remote, BUT

you are expected to be available during Eastern Time working hours

.

Benefits

Generous stock option compensation Top-tier health and benefits coverage Fully remote team * Opportunities to lead technical efforts as the team scales.