Position : Deep Learning Engineer – Computer Vision & Autonomy
Engagement Type : Remote
Location : Remote
Budget : 1.50 LPM + GST
EXP 7-9+ YOE
Position Overview :
An experienced Deep Learning Engineer specializing in Computer Vision, Sensor Fusion, and Multimodal AI
to advance R&D; in autonomous aerial systems and geospatial intelligence, working with large-scale
datasets for drone flight, sensor data integration, and vision-based autonomy.
Key Responsibilities :
- Design and develop deep learning-based perception systems for drones and autonomous platforms
leveraging vision, LiDAR, radar, and IMU sensor data
Build and optimize multimodal fusion architectures combining image, video, and geospatial sensor datafor real-time decision-making
Implement and fine-tune object detection and segmentation models including RCNN, Fast R-CNN, MaskR-CNN, YOLOv5, SAM, and zero-shot models
Conduct research and experimentation on large-scale image and video analytics, 3D reconstruction, andscene understanding
Develop scalable pipelines for model training, hyperparameter tuning, and inference optimization usingTensorFlow / PyTorch, TensorBoard, and distributed computing (Ray, Dask, Spark)
Lead model deployment across GCP-based workflows and design cloud-native AI inference automationsystems
Collaborate with drone engineers to integrate AI models into flight programs and edge devices ensuringlow-latency inference and autonomy
Work with annotation teams using Labelbox, Supervisely, or CVAT to enhance dataset quality andlabeling accuracy
Maintain compliance with geospatial AI data security and regulatory standards ensuring ethical AIdeployment and adherence to data-handling protocols
Required Skills :
Deep LearningComputer VisionPyTorchTensorFlowObject detection and segmentation architectures (RCNN, YOLO, SAM)Multichannel geospatial datasetsSensor fusion3D point cloud processingPythonDistributed computing (Ray, Dask, Spark)Cloud-based AI workflows (GCP preferred)Model compression and quantizationPerformance optimization for on-device inferenceData annotation tools3D reconstruction techniquesBachelor’s or Master’s in Computer Science, Machine Learning, Engineering, or related fieldEligibility for SECRET-category background checksCompliance with geospatial and high-resolution imagery regulationsPreferred (Bonus) Skills :
AWSAzureExperience with edge AI devicesImmediate availability or within 30 days’ noticeFamiliarity with ethical AI development and regulatory compliance