Machine Learning Engineer - Computer Vision

Jumio; Palo Alto (CA); Hybrid; USD 180,000 - 260,000; Full time

Job summary

Jumio in Palo Alto is seeking a Principal ML Engineer to lead the design and deployment of state-of-the-art computer vision biometrics systems, focusing on face attributes, detection, quality, and recognition.

You will architect end-to-end ML pipelines, curate balanced training data, generate synthetic samples to address quality and diversity gaps, and drive rigorous fairness analysis across diverse datasets.

Qualifications

• 5+ years of industry experience in Machine Learning.
• Deep expertise in computer vision and biometrics.
• Understanding sources of algorithmic bias in Computer Vision and mitigating disparate impact.
• Proficiency in Python and ML libraries; ability to write clean, production-ready code.
• Experience deploying ML models on AWS and scaling training jobs on multi-GPU clusters.

Responsibilities

• Lead the design and development of computer vision systems for biometrics (face attributes, detection, quality, and recognition).
• Perform rigorous fairness analysis and benchmarking across datasets and operating conditions.
• Architect, train, and optimise models using PyTorch, TensorFlow, and/or JAX.
• Own and evolve end-to-end ML pipelines from data ingestion to deployment.
• Design automated pipelines (Airflow) for data ingestion and cleaning.
• Curate balanced training sets and generate synthetic data to address quality and diversity gaps.
• Production Engineering: optimise models for low-latency inference and deploy on AWS.
• Mentor ML engineers, conduct code/design reviews, and drive best practices.

Skills

Python

Computer Vision

Biometrics

Machine Learning

Fairness & Ethics

Mentoring

End-to-end ML pipelines

Production-ready code

Tools

PyTorch

TensorFlow

JAX

OpenCV

Pillow

Airflow

TensorRT/ONNX

AWS SageMaker

EC2

EKS

Job description

Responsibilities:

• Lead the design and development of computer vision systems for biometrics (face attributes, detection, quality, and recognition).
• Rigorous fairness analysis and benchmarking of biometric models across various datasets and operating conditions.
• Architect, train, and optimise models using PyTorch, Tensorflow, and/or JAX.
• Own and evolve end-to-end ML pipelines, from data ingestion to deployment.
• Design automated pipelines (Airflow) for data ingestion and cleaning.
• You will be responsible for curating balanced training sets and generating synthetic data to address both quality and diversity gaps.
• Production Engineering: Own the path to production. Optimise models for low-latency inference (quantisation, distillation, TensorRT/ONNX) and manage deployment on AWS.
• Mentor ML engineers, conduct code/design reviews, and drive technical best practices across the Computer Vision team.

Requirements:

• Experience: 5+ years of industry experience in Machine Learning.
• Deep expertise in computer vision and biometrics.
• Fairness and Ethics: You understand the sources of algorithmic bias in Computer Vision and have practical experience measuring and mitigating disparate impact.
• Strong Engineering: Expert proficiency in Python (both machine learning and vision libraries such as Pillow, OpenCV, PyTorch, etc). You write clean, modular, production-ready code.
• Systems Architecture: Experience designing end-to-end ML pipelines (Data to Train to Deploy) and working with workflow orchestrators like Airflow.
• Cloud Native: Hands-on experience scaling training jobs on multi-GPU clusters and deploying services on AWS (SageMaker, EC2 EKS).