Machine Learning Specialist, SSA

GHGSAT

Machine Learning Specialist designing and validating machine learning models for astro-dynamic data at NorthStar Earth & Space. Working in a hybrid environment in Montreal, Quebec.

Posted 7/25/2026full-timeMontréal • 🇨🇦 CanadaMid-LevelSeniorWebsite

Core Competencies

Role fit

Core Competencies

Use this summary to align your resume positioning with the role.

Demonstrates expertise in designing and implementing machine learning and deep learning models, with a strong foundation in probability, statistics, and optimization. Proficient in deploying models to cloud infrastructures and embedded devices while adhering to software engineering best practices.

Highest-signal resume keywords

Machine Learning Model DevelopmentDeep Learning Frameworks (PyTorch)Python ProgrammingAstrodynamics Data AnalysisBilingual in French and English

ATS Keywords

Tailor your resume

Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Hard Skills

Machine LearningDeep LearningProbabilityStatisticsOptimizationTime Series AnalysisData ClusteringAlgorithm DocumentationSoftware Component DevelopmentModel Evaluation

Soft Skills

CollaborationCommunication

Tools & Technologies

GitCI/CDScientific Libraries

Certifications & Qualifications

Master's DegreePhD

Industry Keywords

AstrodynamicsEmbedded SystemsCloud InfrastructureModularityScalability

Tech Stack

Tools & technologies

CloudFluxPythonPyTorch

About the role

Key responsibilities & impact

Design, implement, and validate machine learning / deep learning models (supervised and unsupervised)
Extract near-Earth astrodynamics data from noisy images under constrained hardware resources
Identify time series representing an object's dynamics
Cluster time series data
Infer astrodynamics parameters from partial observations
Analyze long-term trends and behavior of objects in orbit
Deploy these models to cloud infrastructures or on embedded (edge) devices
Develop robust, reusable software components (beyond research prototypes)
Collaborate with a multidisciplinary team
Maintain continuous scientific monitoring, synthesize key findings, and translate them into actionable recommendations for technical and non-technical audiences
Evaluate solution performance using simulated and real data
Clearly document algorithms, workflows, and results

Requirements

What you’ll need

Master's degree or PhD in Machine Learning, Physics, Electrical or Computer Engineering, Applied Mathematics, Aerospace, or a related field
Minimum of 5 years of relevant experience
Bilingual in French and English (written and spoken)
Strong fundamentals in machine learning, probability, statistics, and optimization
Hands-on experience with deep learning frameworks (e.g., PyTorch), Python and its scientific libraries, and developing and debugging custom models
Good command of deep learning architectures: convolutional networks, attention-based architectures, adapting pre-trained models or designing models from scratch
Ability to design proofs of concept with production constraints: modularity, scalability, and reproducibility
Good software engineering practices: Git, testing, CI/CD

Benefits

Comp & perks

Health and dental insurance from day one
Flexible hours and hybrid working arrangement