Senior Machine Learning Engineer (Computer Vision)

Location: Munich, Germany

Company

hirify.global and Tools for Humanity build privacy-preserving identity technology, including the Orb, hirify.global ID, and hirify.global App, to help verify that users are real people in an AI-driven internet.

What you will do

• Own face machine learning projects from problem definition and data preparation through experimentation, evaluation, production validation, and monitoring.
• Improve biometric identification, face verification, uniqueness detection, and anti-spoofing models using deep learning, classical computer vision, and image processing.
• Work with face datasets, collection and labeling requirements, difficult samples, failure modes, and evaluation methodology.
• Build regression evaluation and monitoring pipelines covering data drift, score distributions, attack patterns, cohort-specific regressions, and unexpected model behavior.
• Lead applied ML initiatives, design ablations, evaluate research, and determine when systems are ready for production.
• Write technical proposals, experiment reports, post-launch analyses, and design documents while helping establish team-wide engineering and scientific standards.

Requirements

• Significant hands-on experience training, evaluating, and shipping deep learning systems for computer vision.
• Practical understanding of latency and memory constraints, model training, data pipelines, augmentations, architecture selection, loss functions, optimization, and failure analysis.
• Strong foundations in classical computer vision and image processing, including OpenCV, NumPy, or equivalent tools.
• Fluency in Python and a modern deep-learning framework such as PyTorch.
• Experience designing production evaluations with metrics, thresholds, calibration, dataset construction, slicing, leakage prevention, and regression analysis.
• Ability to write maintainable research and production-quality code and communicate technical decisions clearly.

Nice to have

• Experience with biometric verification or identification, metric-learning losses, presentation attack detection, liveness detection, or adversarial ML evaluation.
• Experience optimizing and deploying ML models on edge or mobile devices, including quantization, pruning, distillation, or NPU and embedded deployment.
• Hands-on Rust experience for high-performance code paths.
• Background in sensors, imaging, computational photography, camera ISPs, privacy-preserving computation, or secure multi-party computation.

Culture & Benefits

• Work across Face, Iris, Mobile, ML Infrastructure, MLOps, Orb software, Proof of Personhood, and Product teams.
• Use deep learning, classical computer vision, and hybrid methods pragmatically according to system requirements.
• Operate on systems deployed at global scale, with strict latency, memory, privacy, and reliability constraints.
• Work in a multidisciplinary organization spanning hardware, software, AI, cryptography, mobile engineering, and global operations.