Machine Learning Engineer

About the role

We are seeking a senior machine learning professional to advance our biometric identity verification systems. You will be instrumental in developing and deploying advanced face recognition technologies, ensuring their performance and integrity. This role offers the chance to own critical components of our machine learning infrastructure from conception to production.

Key facts

What you'll do

• Drive the creation and enhancement of computer vision systems for biometric applications, including face attribute analysis, detection, quality assessment, and recognition.
• Conduct thorough evaluations of biometric model fairness and performance across diverse datasets and conditions.
• Design, train, and refine models using frameworks like PyTorch, Tensorflow, or JAX.
• Manage and improve the entire machine learning lifecycle, from data acquisition to model deployment.
• Build automated workflows for data processing and preparation, including curating balanced datasets and generating synthetic data to address gaps.
• Optimize models for efficient, low-latency inference and manage their deployment on cloud infrastructure.
• Provide technical guidance to other machine learning engineers and promote best practices within the team.

Requirements

• Minimum of 5 years of industry experience in machine learning, with at least 3 years focused on biometrics or face analysis.
• Profound understanding of computer vision and biometrics, particularly in face recognition.
• Demonstrated experience in identifying and mitigating algorithmic bias in computer vision models.
• Strong programming skills in Python, including proficiency with machine learning and computer vision libraries such as Pillow, OpenCV, PyTorch, etc., and a track record of writing production-ready code.
• Experience designing and implementing end-to-end machine learning pipelines and using workflow orchestration tools like Airflow.
• Hands-on experience with scaling model training on multi-GPU systems and deploying services on AWS, including SageMaker, EC2, and EKS.

Nice to have

• Published research in top-tier computer vision conferences such as CVPR, ICCV, ECCV, or FG, related to face recognition, image quality, or fairness.
• Experience with large-scale similarity search using vector databases like Milvus or Faiss, and approximate nearest neighbor algorithms.
• Familiarity with privacy and security considerations in biometric systems.
• Experience deploying models to mobile or edge devices using frameworks like CoreML, LiteRT, or TFLite.
• Experience generating synthetic faces using GANs or diffusion models for training purposes.
• Excellent communication abilities.

Skills & tools

• Python
• PyTorch
• Tensorflow
• JAX
• Computer Vision Libraries (e.g., OpenCV, Pillow)
• AWS (SageMaker, EC2, EKS)
• Airflow
• Model Optimization Techniques (e.g., quantization, distillation, TensorRT, ONNX)

Practical notes

• Jumio is committed to diversity and inclusion, welcoming applications from all backgrounds.
• Jumio is a technology company focused on preventing identity fraud and financial crime through AI, biometrics, and machine learning.