Machine Learning Engineer

About the company

• Jumio is a B2B technology company dedicated to eradicating online identity fraud, money laundering and other financial crimes
• Leading provider of online identity verification, eKYC and AML solutions

Responsibilities

• Lead design and development of computer vision systems for biometrics (face attributes, detection, quality, recognition)
• Rigorous fairness analysis and benchmarking of biometric models
• Architect, train, and optimize models using PyTorch, TensorFlow, and/or JAX
• Own end-to-end ML pipelines from data ingestion to deployment; design automated pipelines with Airflow
• Curate balanced training sets and generate synthetic data
• Optimize models for low-latency inference (quantization, distillation, TensorRT/ONNX) and manage deployment on AWS
• Mentor ML engineers, conduct code/design reviews

Requirements

• Strong industry experience in ML dedicated to biometrics or face analysis
• Deep expertise in computer vision and biometrics, especially face recognition
• Understanding of algorithmic bias and practical experience mitigating disparate impact
• Expert proficiency in Python and vision libraries (Pillow, OpenCV, PyTorch)
• Experience designing end-to-end ML pipelines and working with Airflow
• Hands-on experience scaling training on multi-GPU clusters and deploying on AWS (SageMaker, EC2, EKS)
• Nice to have: publications in CVPR/ICCV/ECCV/FG, vector databases (Milvus, Faiss), ANN search, edge/mobile (CoreML, LiteRT, TFLite), GANs/diffusion models

Conditions

• Remote in India
• Final job level determined after interview process