Senior Data Scientist

Indonesia·Jakartasenior

Data ScientistData

0 views0 saves0 applied

Apply Now

Quick Summary

Overview

Senior Computer Vision & Deep Learning Scientist — Liveness & Deepfake Detection Our mission is to create innovative, robust, and user-friendly digital identity solutions.

Key Responsibilities

Design, train, and deploy CV/DL models for presentation attack detection (PAD) and deepfake detection (print/replay, 2D/3D masks, screen replays, injection, face-swap/GAN/diffusion).

Requirements Summary

Advanced degree in a quantitative field or equivalent experience, and 3+ years building/launching computer vision & deep learning models (biometrics, PAD, or deepfake detection preferred).

Technical Tools

awsazuregcppythonpytorchtensorflowci-cddeep-learningecommerce

Responsibilities

~1 min read

→Design, train, and deploy CV/DL models for presentation attack detection (PAD) and deepfake detection (print/replay, 2D/3D masks, screen replays, injection, face-swap/GAN/diffusion).
→Own datasets end-to-end: collection strategy, labeling specs, quality gates, hard-negative mining, bias/fairness audits.
→Build realistic benchmarks and red-team suites; report metrics (FAR/FRR), ROC/PR, calibration; run ablations and adversarial stress tests.
→Ship models with clear latency/SLA targets; partner with engineers on scalable inference APIs and monitoring (drift, false-positive hot spots).
→Translate fraud patterns into model features and detection rules; collaborate with product, fraud ops, and key customers.
→Track state-of-the-art CV/DL and adopt techniques that improve security, latency, or cost; align with ISO/IEC 30107 (PAD) best practices.
→Work independently or in a team to solve complex problem statements

Requirements

~1 min read

Advanced degree in a quantitative field or equivalent experience, and 3+ years building/launching computer vision & deep learning models (biometrics, PAD, or deepfake detection preferred).
Strong CV/DL fundamentals: modern backbones/transformers, temporal models, contrastive/metric learning, robustness techniques.
Proficient in Python and PyTorch (or TensorFlow); OpenCV/FFmpeg; proven track record taking models from notebook → production with experiment tracking, CI/CD, and post-deploy monitoring.
Clear communication, ownership mindset, and bias to ship.

Nice to Have

~1 min read

Deepfake forensics (GAN/diffusion artifacts, watermark/signature checks).
On-device/low-latency inference (TensorRT, ONNX Runtime, TFLite, Core ML, NNAPI), CUDA kernels, or inference compilers.
Familiarity with cloud platforms like AWS, GCP, or Azure for model deployment.
Familiarity with ISO/IEC 30107 (PAD), ISO/IEC 19795 (biometric performance), ISO/IEC 39794 (biometric data interchange).
Synthetic data/simulation to cover rare attacks.

VIDA is a government-licensed certificate authority (CA) operating under Indonesia’s Ministry of Electronics and Information Technology. Our key offerings include:
Legally valid digital signatures ensuring secure and scalable identity solutions.
Trusted identity verification services for industries such as BFSI, eCommerce, telecommunications, and healthcare.
Advanced AI-driven fraud prevention: VIDA leverages sophisticated AI models to detect and prevent deepfake frauds, enhancing security and trust in digital interactions.
Seamless integration to help businesses reduce onboarding friction while prioritizing user privacy and data security.
For more information, you may visit our website at https://vida.id