3 Detectron2 Jobs

You will be working at ClearTrail, where the focus is on developing solutions to empower organizations dedicated to ensuring the safety of their people, places, and communities. With over 23 years of experience, ClearTrail has been a trusted partner for law enforcement and federal agencies worldwide in safeguarding nations and enriching lives. As part of the team, you will contribute to the future of intelligence gathering by creating artificial intelligence and machine learning-based lawful interception and communication analytics solutions to address some of the world's most challenging problems. Your role will involve developing and training machine learning models that leverage drone, satellite, and real-time video data for complex visual understanding tasks. You should have a minimum of 10-12 years of relevant experience for this position. Key responsibilities of the role include: - Building machine learning and deep learning models for image and video classification, segmentation, and spatiotemporal analysis. - Developing fusion methods to align and combine data from satellite, drone, and ground footage. - Applying advanced techniques such as multi-scale learning, temporal modeling (e.g., 3D CNNs, transformers), and sensor fusion. - Conducting model evaluation and optimization across various data sources. Essential skills for this role include: - Strong proficiency in Python coding and data manipulation using libraries such as NumPy, Pandas, and SciPy. - Expertise in vision/model libraries like MMDetection, Detectron2, and OpenCV. - Deep learning experience with PyTorch, TensorFlow, and video models such as TimeSformer, SlowFast, I3D, and Yolo. - Knowledge of satellite/drone geospatial fusion, GPS/IMU metadata, and scene alignment. - Familiarity with time series analysis, motion tracking, and optical flow using tools like RAFT and FlowNet. - Understanding of remote sensing libraries such as Rasterio, GDAL, GeoPandas, and xarray. If you are passionate about leveraging machine learning and artificial intelligence to address complex challenges in intelligence gathering, this role at ClearTrail offers an exciting opportunity to make a meaningful impact.,

You will be responsible for developing and training machine learning models that leverage drone, satellite, and real-time video data to tackle complex visual understanding tasks. Your primary focus will be on building ML/DL models for image and video classification, segmentation, and spatiotemporal analysis. Additionally, you will be tasked with developing fusion methods that align and merge data from satellite, drone, and ground footage sources. To excel in this role, you must have a minimum of 10-12 years of relevant experience. You should possess strong Python coding skills along with expertise in data manipulation using libraries such as NumPy, Pandas, and SciPy. Proficiency in vision/model libraries such as MMDetection, Detectron2, and OpenCV is essential. Moreover, you must have hands-on experience in deep learning frameworks like PyTorch and TensorFlow, particularly in developing video models with TimeSformer, SlowFast, I3D, Yolo, among others. Your expertise should extend to satellite/drone geospatial fusion, GPS/IMU metadata, and scene alignment. Familiarity with time series analysis, motion tracking, and optical flow techniques (e.g., RAFT, FlowNet) is beneficial. In addition, knowledge of remote sensing libraries like Rasterio, GDAL, GeoPandas, and xarray will be advantageous for this role. Your responsibilities will also include model evaluation and optimization across various data sources, ensuring the delivery of high-quality solutions that contribute to the future of intelligence gathering.,

Youll make a difference by: We are seeking a highly skilled and motivated AI/ML Engineer having experience in the field of artificial intelligence and machine learning. The ideal candidate should have expertise in developing and implementing AI/ML algorithms, a strong background in computer vision, hands-on experience with open-source Generative AI models, and a solid foundation in mathematical and statistical principles. As part of our dynamic AI team, you will work on designing, building, and optimizing AI systems with a focus on innovative solutions. Key Responsibilities: Developing and implementing AI-based solutions to enhance the efficiency, effectiveness, and speed of our R&D processes. Continuously monitoring and evaluating implemented AI solutions to ensure their performance and continuous improvement. Promoting knowledge exchange and competency development in the field of AI within the company Develop POC's to solve real-world problems in various domains such as text summarization, chatbots, language translation, image generation, data augmentation, and content synthesis, preferably with locally hosted models, open-source tools and frameworks. AI Model Optimization: Focus on optimizing AI models for performance, efficiency, and scalability, ensuring that they run effectively in offline environments without the need for cloud-based solutions. Computer Vision Applications: Work on AI-driven computer vision projects, including but not limited to image classification, object detection, segmentation, and image enhancement. Implement innovative computer vision algorithms for solving practical problems. AI & ML Algorithms: Leverage machine learning (ML) techniques to improve and fine-tune generative AI models and computer vision systems. Familiarity with both supervised and unsupervised learning techniques is essential. Research and Development: Stay up to date with the latest advancements in Generative AI, Computer Vision, and related fields. Experiment with new techniques and frameworks to continually improve the quality and capabilities of our solutions. Collaboration: Work closely with data scientists, software engineers, and product teams to deliver high-quality AI-based products. Contribute to the teams technical discussions and knowledge sharing. Model Deployment & Maintenance: Work on deploying and maintaining AI models, ensuring reliability and performance. Set up and manage model training and inference pipelines. Qualifications: Education: bachelors or masters degree in computer science, mathematics, or a comparable field with a focus on artificial intelligence Experience: Minimum of 3 to 4 years of hands-on experience in AI/ML development or data science, with a strong focus on Generative AI and Computer Vision. Experience working with open-source, locally hosted models is highly preferred. Technical Skills: Proficiency in deep learning frameworks such as TensorFlow, PyTorch, or openVINO. Experience with GenAI or Large Language Models or NLP for training, fine-tuning, and evaluating LLMs Experience in computer vision algorithms and frameworks (e.g., OpenCV, Detectron2, YOLO). Strong knowledge of machine learning algorithms (supervised, unsupervised, reinforcement learning). Familiarity with deploying AI models in offline environments and working with locally hosted models. Strong mathematical/statistical skills and the ability to clearly understand, define and communicate complex concepts in this area. Programming Skills: Advanced proficiency in Python and relevant AI/ML libraries (NumPy, SciPy, scikit-learn). Familiarity with version control tools (e.g., Git). Experience with C++ along with Docker, Kubernetes, or other containerization technologies is a plus. Problem Solving: Strong analytical and problem-solving skills with the ability to tackle complex and unstructured problems in AI and computer vision. Communication Skills: Ability to communicate complex technical concepts clearly to both technical and non-technical stakeholders. Nice-to-Have: Familiarity with AI hardware accelerators (e.g., GPUs, TPUs) and distributed computing. Knowledge of AI ethics and privacy considerations, especially in the context of offline AI. Desired Skills: 2-5 years of experience is required. Great Communication skills. Analytical and problem-solving skills