Senior ML Engineer (Computer Vision)

Location: Hybrid in Berlin, Germany; willingness to work on-site in Berlin is required.

Company

hirify.global develops satellite analytics products that turn Earth observation data into reliable, actionable information, including the Twinspector satellite programme.

What you will do

• Design, train, and iterate on computer vision models for detection, segmentation, classification, change analysis, 3D reconstruction, and image matching using very high-resolution satellite imagery.
• Adapt state-of-the-art computer vision and remote-sensing research into validated prototypes and production baselines.
• Compress, quantize, and optimize models for constrained and embedded targets, including on-device and onboard inference.
• Build scalable training and evaluation pipelines across AWS and secure on-premises environments using experiment tracking and reproducible workflows.
• Deliver production-ready inference interfaces, model packaging, deterministic evaluation, and monitoring.
• Collaborate with data annotation specialists, product teams, external research partners, and the Twinspector satellite programme.

Requirements

• Strong computer vision and machine learning fundamentals, including representation learning, supervision strategies, evaluation design, debugging, and optimization.
• Practical experience with multiple computer vision problem types and depth in at least one imaging domain.
• Strong Python engineering skills and deep experience with PyTorch and large-scale deep learning model training.
• Strong understanding of ML experimentation, versioning, and tracking.
• Background in remote sensing, computer science, physics, or a related field, or equivalent practical experience.
• Eligibility to obtain German security clearance (Sicherheitsüberprüfung) and willingness to work on-site in Berlin.

Nice to have

• Experience deploying models on constrained compute, edge, or embedded devices through compression, quantization, and optimization.
• Hands-on experience with satellite or remote-sensing imagery, SAR, geospatial foundation models, or VLMs.
• Experience with Ray, Prefect, AWS, secure on-premises or HPC environments, Docker, DVC, and SLURM.
• Experience with GDAL, Rasterio, GeoPandas, STAC, PostgreSQL, synthetic data generation, sim2real, or domain adaptation.
• PhD in remote sensing, computer science, physics, applied mathematics, or a related field.

Culture & Benefits

• Flexible working hours and a hybrid work model.
• Career development support, autonomy, and opportunities to contribute ideas.
• Overtime is limited and offset with time off and rest.
• Internal workshops, knowledge-sharing sessions, journal clubs, and hackathons.
• Central Berlin Kreuzberg office with free fruit, nuts, and drinks, plus Urban Sports membership and BVG subsidy.
• Corporate pension programme, potential employee stock option participation, and an international environment with more than 30 nationalities.