3 months ago
Remote, AustriaSenior
Responsibilities
- Lead the design and development of computer vision and biometric systems for face attributes, detection, quality assessment, and recognition.
- Perform fairness analysis and benchmarking of biometric models across datasets and operating conditions.
- Architect, train, and optimize models using PyTorch, TensorFlow, and/or JAX.
- Own end-to-end ML pipelines from data ingestion through training and deployment, including Airflow-based ingestion and cleaning workflows.
- Curate balanced training datasets and generate synthetic data to address quality and diversity gaps.
- Optimize models for low-latency inference using quantization, distillation, TensorRT, and ONNX.
- Deploy and scale machine learning services and training jobs on AWS.
- Mentor ML engineers, conduct code and design reviews, and drive technical best practices across the Computer Vision team.
Requirements
- 5+ years of industry experience in machine learning, including at least 3 years dedicated to biometrics or face analysis.
- Deep expertise in computer vision, biometrics, and face recognition.
- Practical experience measuring and mitigating algorithmic bias and disparate impact in computer vision.
- Expert proficiency in Python and machine learning and computer vision libraries such as Pillow, OpenCV, and PyTorch.
- Experience designing end-to-end ML pipelines and working with workflow orchestrators such as Airflow.
- Hands-on experience scaling training jobs on multi-GPU clusters and deploying services on AWS, including SageMaker, EC2, and EKS.
- Preferred experience with research publications in CVPR, ICCV, ECCV, or FG related to face recognition, image quality assessment, or fairness.
- Preferred experience with vector databases such as Milvus or Faiss and approximate nearest neighbor search.
- Preferred familiarity with privacy, security, and compliance in biometric systems.
- Preferred experience porting models to mobile or edge devices using CoreML, LiteRT, or TFLite.
- Preferred experience using GANs or diffusion models to generate synthetic faces for training.
- Strong communication skills.
Categories
About Jumio
Jumio builds identity verification, document verification, and KYC solutions for enterprises, delivered via APIs and web workflows to reduce fraud and meet compliance. Privately held and founded in 2015 with headquarters in Jaipur, India, it verifies government-issued IDs and biometrics with liveness checks from 200+ countries, serving sectors such as financial services, fintech, e-commerce, and online gaming.