SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Salary: USD 156,000 - 186,000 / annual
Muon Space is building infrared imaging satellite missions for global wildfire detection, weather monitoring, and environmental observation. The IR Data Products team develops the analytics pipeline that transforms raw multispectral imagery from spacecraft into calibrated, orthorectified, analysis-ready products with strict latency requirements—fast enough to support active wildfire response.
In this role, you will own the production data processing pipeline that ingests raw frames from orbit, performs radiometric calibration and geolocation, orthorectifies imagery into map-projected tiles, and derives fire detections and perimeters. The system operates under hard latency budgets and scales across a growing satellite constellation.
Key responsibilities include building and maintaining production pipelines for infrared imagery processing; optimizing pipeline performance through profiling, parallelization, and overhead elimination; implementing workflow orchestration for continuous, automated processing across multiple satellites; building monitoring, alerting, and operational tooling; participating in on-call rotations; collaborating with remote sensing scientists to translate algorithms into production-ready code; contributing to code review and testing practices; diagnosing and fixing data quality and processing failures; and learning domain-specific topics including remote sensing techniques and geospatial data engineering.
You will work with a distributed, interdisciplinary team of scientists, engineers, and data specialists. This is hands-on production software engineering where your work directly impacts real users and real-world wildfire response operations.
Required qualifications: BS/MS/PhD in Computer Science, Engineering, or physical science (or equivalent); 5+ years (BS) or 3+ years (MS) of professional experience beyond internships; solid Python skills with experience writing tested, reviewed, and maintained code; familiarity with cloud infrastructure (AWS preferred) and containerized deployment; comfort working with large-scale data; ability to work in distributed teams; willingness to learn the science domain deeply enough to validate correctness.
Preferred: experience with geospatial tooling (XArray, COG, GeoTIFF, NetCDF, GDAL, Zarr); workflow orchestration (Flyte, Airflow); performance profiling of data-intensive systems; satellite/remote sensing/scientific imagery pipelines; infrastructure-as-code (Terraform); production on-call operations.
