Senior Computer Vision / ML Engineer

RELX (Singapore) Pte Ltd; Sydney; Remote; AUD 120,000 - 180,000; Full time

Job summary

RELX (Singapore) Pte Ltd, within LexisNexis Risk Solutions, seeks researchers to advance identity verification, fraud prevention and security through CV/ML, liveness detection, and adversarial defenses.

You will explore deep learning, experiment rigorously, and push toward production-ready systems with strong software foundations. Remote, globally distributed team with rights for Australia work.

Qualifications

• Deep knowledge of computer vision, ML and DL foundations.
• Demonstrated ability to solve open-ended research and engineering problems.
• Strong experience with Python and PyTorch or equivalent.
• Experience designing controlled experiments and analyzing model behavior.
• Ability to translate research concepts into production systems.
• Strong software engineering fundamentals including CUDA/ONNX.

Responsibilities

• Research and invent in CV, biometrics, liveness, deepfake detection, and adversarial attacks.
• Develop novel attack vectors and robust defenses.
• Design, train, evaluate, and optimize deep learning models for image/video data.
• Take ideas from research to production through benchmarking and deployment.
• Stay close to AI research and translate advances into product improvements.

Skills

Computer vision

Machine learning

Deep learning

Experiment design

Production-ready research

Software engineering fundamentals

Education

Bachelor's or Master's in CS/ML/Math/Engineering

Tools

Python

PyTorch

CUDA

TensorRT

ONNX

Job description

About the Business

LexisNexis Risk Solutions helps organizations assess and manage risk across identity verification, fraud prevention, financial crime compliance, credit risk, and customer data management.

About Our Team

IDVerse builds identity verification technology to fight fraud at global scale. Our systems must stay effective against evolving attacks including spoofing, deepfakes, injection attacks, and AI-generated fraud. We are a team of researchers and engineers who think from first principles, experiment rigorously, and invent new approaches as we continuously improve our systems.

What You'll Do

Research and invent: Investigate difficult problems in computer vision, biometrics, liveness, anti-spoofing, deepfake detection, generative AI, and adversarial attacks. Form hypotheses, run controlled experiments, and develop conclusions that can be trusted. Understand not only whether something works, but why it works, where it fails, and what to try next.

Red Team Mindset: Develop novel presentation, injection, deepfake, synthetic-media, and AI generated attacks against our systems. Build adversarial evaluations, expose weaknesses, understand their underlying causes, and develop robust defenses.

Build advanced CV/ML models: Design, train, evaluate, and optimize deep learning approaches across image, video, and multimodal data, applying techniques such as representation learning, transformers, generative models, 3D/geometric vision, where appropriate.

Own research through production: Take ideas from research and prototyping through benchmarking, optimization, deployment, and real-world evaluation.

Push the state of the art: Stay close to emerging computer vision and AI research, reproduce and challenge promising ideas, and identify opportunities to turn research advances into meaningful improvements to IDVerse products.

Required qualifications

Deep knowledge of computer vision, machine learning, and deep learning, backed by strong foundations in mathematics, statistics, optimization, or related disciplines.

Demonstrated ability to solve open-ended research and engineering problems, rather than only implementing established solutions.

Strong experience with Python and PyTorch or equivalent modern deep-learning frameworks.

Experience designing controlled experiments, analyzing model behavior and failure modes, and evaluating models against challenging datasets.

Ability to translate research concepts into efficient, reliable production systems.

Strong software engineering fundamentals. Experience with C/C++, CUDA, TensorRT, ONNX.

Bachelor's or Master's degree in Computer Science, Machine Learning, Mathematics, Engineering, or a related discipline, or equivalent demonstrated expertise.

Highly Desirable

PhD or equivalent research experience in computer vision, machine learning, AI, mathematics, or a related field.

Publications, patents, significant open-source contributions, competition results, or other evidence of original technical or research contributions.

Experience with biometrics, liveness / presentation attack detection, deepfakes, synthetic media, adversarial ML, or AI security.

Red-team or adversarial research experience, particularly discovering novel ways to attack, manipulate, or stress-test ML/CV systems.

Familiarity with biometric security and presentation-attack standards such as ISO/IEC 30107.

Location and collaboration

The team is remote and globally distributed. Candidates must have full working rights in Australia.