Location: Remote (with optional office access in multiple locations)
Employment Type: Full-time
About Enqura
Enqura is a fast-growing fintech company delivering AI-driven security and customer experience solutions for financial institutions.
Our mission is to transform self-service banking into fully AI-assisted digital banking. With a global team of over 70 professionals, we empower banks, fintechs, and insurance companies through innovative, secure, and scalable technologies.
Role Overview
We are looking for a Senior AI Engineer to design, train, optimize, and deploy AI models for our digital identity verification platform. In this role, you will work on biometric and document AI systems including face recognition, liveness detection, anti-spoofing, OCR, and document intelligence. The position involves building production grade AI models that operate across both backend infrastructure and mobile environments, ensuring high accuracy, scalability, and efficient real-time performance.
You will contribute to the development of AI systems used in real world identity verification processes, supporting secure digital onboarding and fraud prevention for financial institutions.
Responsibilities
- Develop and train AI models for:
◦ Face recognition and embedding generation
◦ Liveness detection and anti-spoofing
◦ OCR and document data extraction
◦ Document authenticity and fraud detection - Build real time AI pipelines for camera based identity verification processes.
- Deploy and optimize models for:
◦ Backend inference services (high-accuracy models)
◦ Mobile devices and edge environments (lightweight optimized models) - Design and implement AI model serving infrastructure:
◦ Expose models via APIs
◦ Integrate models into production systems
◦ Build scalable inference pipelines - Optimize AI models using:
◦ Quantization (INT8 / FP16)
◦ Model compression
◦ Knowledge distillation
◦ Mobile optimization techniques - Improve AI inference performance by optimizing:
◦ CPU / GPU / NPU utilization
◦ Memory footprint
◦ Frame-time latency
◦ Battery consumption - Benchmark and profile model performance on real hardware.
- Design hybrid inference strategies combining:
◦ On-device inference
◦ Server-side fallback inference - Collaborate with mobile, backend, and product teams to integrate AI systems into production environments.
Qualifications
- Strong experience in Computer Vision and AI model development
- Experience training models using:
◦ PyTorch
◦ TensorFlow
◦ ONNX - Experience developing AI systems for:
◦ Face recognition
◦ Liveness detection and anti-spoofing
◦ OCR and document image processing
◦ Document authenticity and fraud detection - Experience deploying and serving AI models in production environments
- Experience deploying AI models to:
◦ Mobile devices
◦ Edge environments - Knowledge of mobile AI deployment frameworks:
◦ TensorFlow Lite
◦ CoreML
◦ ONNX Runtime Mobile - Experience designing:
◦ Mobile inference pipelines
◦ Real-time camera-based inference systems - Experience optimizing models using:
◦ Quantization
◦ Model compression
◦ Knowledge distillation - Experience profiling and optimizing model latency on real hardware
- Understanding of resource-constrained AI systems, including optimization for:
◦ CPU / GPU / NPU utilization
◦ Memory footprint
◦ Battery consumption
◦ Frame-time performance - Experience building scalable AI services, including:
◦ REST APIs
◦ Model serving infrastructure
◦ Inference pipelines - Experience with digital identity verification, biometric systems, or KYC technologies is a strong plus.
- Professional proficiency in written and spoken English
What We Offer
- Career growth in a global, AI-driven fintech company.
- Flexible remote-first working model with optional office access
- Dynamic, innovative, and international work environment.
- Opportunity to collaborate with global customers.
- Continuous learning and professional development support.