AI Computer Vision Engineer – eKYC (Face Matching & Liveness Detection)

Design, train, evaluate, and deploy computer vision models for face matching (selfie ↔ document / reference image) and face liveness detection / anti- spoofing (detecting attacks from photos, replay, masks, deepfake, etc.).
Monitor model performance in production: metrics like FAR / FRR, ROC / AUC, error cases under challenging conditions (low light, extreme pose, blur).
Build data pipelines: image/video collection, preprocessing, augmentation, alignment, quality checks, normalization.
Continuously iterate and improve based on real- world feedback, edge cases, and adversarial examples.
Optimize models for on- device inference (mobile, edge) — focus on resource constraints (latency, memory, compute).
Research state- of- the- art techniques in face recognition, spoof detection, domain generalization, and apply to real- world constraints.
Collaborate with mobile / SDK / backend teams to integrate models securely into client applications.

3+ years of experience in computer vision / face recognition / liveness detection / anti- spoofing.
Good communication skills; ability to explain trade offs to product, mobile, and operations teams.
Strong programming skills in Python; familiarity with frameworks like PyTorch, TensorFlow, ONNX, and mobile inference frameworks.
Experience with face detection, face alignment, landmark detection, preprocessing, and image normalization workflows.
Proven track record of deploying vision models to production, ideally on mobile / edge platforms.
Strong problem solving, debugging, and analytical skills.
Experience optimizing models (quantization, pruning, knowledge distillation) for deployment under resource constraints.
Experience in liveness detection methods: texture / reflection / depth cues / motion cues / multimodal approaches.
Bachelor’s / Master’s / PhD in Computer Science, AI, Electrical Engineering, or related fields.

Laptop, Chế độ bảo hiểm, Du Lịch, Chế độ thưởng, Chăm sóc sức khỏe, Đào tạo, Tăng lương, Nghỉ phép năm

Cập nhật gần nhất lúc: 2026-03-26 10:15:04