Data Scientist

Key ResponsibilitiesDesign, develop, and deploy computer vision models for real-world applications such as object detection, image segmentation, OCR, and video analyticsBuild scalable, low-latency inference pipelines for real-time or near real-time systemsDevelop production-quality Python code with strong engineering principles (modular design, testing, maintainability)Deploy and manage ML models using APIs and microservices architecturesWork with cloud or edge-based environments for model deployment and optimizationImplement monitoring, model evaluation, and performance tracking (e.g., drift detection, A/B testing)Collaborate with cross-functional teams including product managers, engineers, and data teamsAnalyze data quality, perform dataset annotation/augmentation, and troubleshoot model performance issuesOptimize models for performance, accuracy, and computational efficiency (GPU/latency improvements)Required Skills & ExperienceStrong hands-on experience in Computer Vision with real-world, production-deployed systemsProficiency in Python with solid software engineering fundamentals (OOP, APIs, testing frameworks)Experience with CV frameworks/tools such as YOLO, OpenCV, Detectron2, PyTorch, TensorFlowProven experience deploying ML models into production environments (not just experimentation)Experience with Docker, Kubernetes, CI/CD pipelines, and model deployment tools (e.g., MLflow)Strong understanding of APIs and microservices architecture (FastAPI, Flask, etc.)Experience working with real-time or low-latency systemsKnowledge of model monitoring, drift detection, and performance tuningStrong understanding of the data lifecycle including annotation, augmentation, and data quality challengesAbility to debug model performance issues and explain trade-offs in model design