Ai Engineer

About Ezlo InnovationEzlo Innovation is a leading IoT platform developer powering smart home and property management solutions across 60+ countries. Our family of brands—including Vera, MiOS, Fortrezz, and Centralite—brings nearly 50 years of combined experience in home automation and IoT markets. We deliver cloud-to-ground, white-label IoT solutions to security dealers, property management companies, builders, utilities, and retail partners worldwide.About the RoleWe're looking for a Machine Learning Engineer to own and advance our CloudML video analytics platform. This system processes video from smart home cameras to detect objects including people, vehicles, animals, packages, faces, and license plates. You'll be the primary developer responsible for this project while collaborating with our broader cloud infrastructure team.This role focuses heavily on ML model performance —improving detection accuracy, reducing false positives / negatives, and optimizing model efficiency for real-time video processing at scale.The PlatformCloudML v2 is a production video object detection service built on : ML / Computer Vision : YOLO v8 / v11, YOLOWorld (zero-shot detection), PyTorch, OpenCV, face-recognition, OpenALPRBackend : Python 3.11, FastAPI, Redis Queue (RQ)Infrastructure : Kubernetes, Helm, Docker, NVIDIA GPUs (CUDA 12.6)Observability : OpenTelemetry, structured loggingThe system processes MP4 video files through a multi-stage pipeline : download, validation, frame extraction, multi-model inference (standard objects, packages, faces, license plates, barcodes), and webhook delivery of results.Primary ResponsibilitiesModel Performance & AccuracyImprove detection accuracy across all object classes (person, vehicle, animal, package, face, license plate)Reduce false positive and false negative ratesFine-tune and retrain YOLO models on domain-specific datasetsEvaluate and integrate newer model architectures as they become availableDevelop robust evaluation metrics and benchmarking pipelinesModel Efficiency & OptimizationOptimize inference speed and resource utilizationImplement model quantization, pruning, or distillation techniquesBalance accuracy vs. latency tradeoffs for real-time processingOptimize frame skip strategies and batch processingProfile and eliminate performance bottlenecks in the inference pipelineOngoing DevelopmentMaintain and extend the existing detection pipelineAdd support for new object classes as business needs evolveImprove hotzone (region-of-interest) detection logicEnhance face recognition matching accuracyCollaborate with the cloud team on infrastructure and scalingRequired QualificationsStrong experience with object detection models, particularly YOLO family (v5 / v8 / v11), and understanding of model training, fine-tuning, and evaluationHands-on experience with PyTorch for model development and optimizationComputer vision fundamentals : image / video processing, frame extraction, bounding box handling, NMS, confidence thresholdsPython proficiency with production-quality code practicesExperience deploying ML models in production environments (containerization, GPU inference, batching strategies)Understanding of model optimization techniques : quantization, TensorRT, ONNX conversion, etc.Familiarity with Linux / Docker / Kubernetes environmentsPreferred QualificationsExperience with video analytics or surveillance systemsBackground in face recognition systemsExperience with license plate recognition (ALPR / OCR)Familiarity with zero-shot detection models (YOLOWorld, CLIP-based approaches)Experience with dataset curation, annotation, and augmentationKnowledge of edge deployment considerations (model size, latency constraints)Experience with distributed job queues (Redis Queue, Celery)Tech Stack You'll Work WithCategoryTechnologiesML FrameworksPyTorch, Ultralytics YOLO, YOLOWorld, OpenCV, SupervisionSpecialized MLface-recognition (dlib), OpenALPR, Tesseract OCR, pyzbarBackendPython 3.11, FastAPI, Redis, RQ (Redis Queue)InfrastructureKubernetes, Helm, Docker, GitLab CI / CDHardwareNVIDIA GPUs, CUDA 12.6ObservabilityOpenTelemetry, structured loggingWhat Success Looks LikeMeasurable improvements in detection accuracy (precision / recall) across object classesReduced inference time per video while maintaining or improving accuracyWell-documented model evaluation pipelines and benchmarksProactive identification and resolution of model performance issuesClear communication with the broader team on ML capabilities and limitationsEmployment DetailsType : Full-timeTeam : Cloud Infrastructure TeamScope : Primary owner of CloudML video analytics platform