Principal Computer Vision Engineer

Why Airtel Africa?

At Airtel, we dont just make things we make things possible. Airtel Africa is on a mission to change the world by connecting people with ideas.  We are building next generation systems to improve the quality of life for 180+ million customers spanned across 14+ countries

Role & responsibilities

• Design, develop, and deploy production-grade Machine Learning and Computer Vision solutions, owning the end-to-end lifecycle from problem definition and experimentation to deployment, monitoring, and continuous improvement.
• Build intelligent document processing and identity verification systems that leverage Computer Vision, OCR, NLP, and Deep Learning techniques to automate KYC workflows, improve data extraction accuracy, and enhance customer onboarding experiences.
• Partner closely with Product, Engineering, and Business stakeholders to translate business requirements into scalable AI-powered solutions.
• Develop and optimize models for document classification, identity information extraction, OCR, object detection, document fraud detection, image quality assessment, and related computer vision challenges.
• Drive model evaluation, performance benchmarking, dataset creation, annotation strategies, and continuous model improvement using robust experimentation frameworks.
• Build scalable ML pipelines and inference services, ensuring high availability, low latency, observability, and operational excellence in production environments.
• Leverage modern AI engineering practices, tooling, and automation across the software development lifecycle to improve development velocity, model reliability, and system scalability.
• Conduct technical design reviews, code reviews, and model reviews with a strong focus on quality, maintainability, security, and responsible AI practices.
• Mentor engineers and provide technical leadership in designing and delivering enterprise-scale AI systems.

Preferred candidate profile

• Bachelors or Master’s in Computer Science, AI, Machine Learning, or significant relevant experience.
• 8+ years of experience building and deploying Computer Vision and Machine Learning solutions in production.
• Strong experience in Identity Verification, OCR, Document AI, Intelligent Document Processing (IDP), and KYC-related use cases.
• Solid expertise in OCR, document parsing and entity extraction, object detection, image classification, segmentation, and identity verification solutions.
• Experience with face matching, liveness detection, and document fraud detection is a plus.
• Hands-on experience with modern deep learning architectures, including CNNs, Vision Transformers (ViTs), multimodal models, and document understanding frameworks.
• Strong expertise in model development, fine-tuning, evaluation, optimization, and dataset curation.
• Proven ability to build custom AI models and domain-specific solutions.
• Proficiency in Python and ML frameworks such as PyTorch, Hugging Face, OpenCV, and TensorFlow.
• Experience deploying and optimizing models using ONNX, TensorRT, OpenVINO, or similar inference frameworks.
• Practical knowledge of MLOps, CI/CD, model monitoring, and cloud-native AI deployments.
• Exposure to Small Language Models (SLMs) and Small Vision Language Models (SVLMs) is highly desirable.
• Strong analytical, problem-solving, communication, and stakeholder management skills.