Computer Vision & Machine Learning Engineer

Job Description   Buzz is revolutionizing the analytics and maintenance of power grid infrastructure through our advanced AI solutions. Our computer vision systems   analyze   critical infrastructure to enhance safety, reliability, and operational efficiency across the power grid network. We're   looking for a Machine Learning Engineer to advance our computer vision initiatives and help build our foundational model capabilities.   You'll   bridge the gap between   cutting-edge   research and production systems ,   reading papers, adapting novel algorithms, and turning them into reliable, deployed models for power grid analysis.   You'll   work within a team of experienced ML engineers, with the autonomy to drive your own projects and the support to keep growing.   Responsibilities Project delivery   Own and deliver end-to-end computer vision projects focused on:   Equipment defect detection Thermal anomaly identification   Vegetation encroachment monitoring Surveillance of closed areas for human and animal intrusion   Scope, plan, and execute your own projects from problem framing through production deployment and monitoring.   Deliver on client projects, translating client requirements and raw data into working computer vision solutions.   Contribute to shared team projects, coordinating with other engineers to deliver against common milestones.   Research and experimentation   Stay current with ML/CV research, identify promising methods, and evaluate their applicability to our domain.   Adapt and implement algorithms from papers, validating against baselines and benchmarking for production viability.   Bring the latest advances in deep learning and generative AI to bear on model training, accuracy, and reliability.   Design and execute experiments with systematic hyperparameter tuning, ablation studies, and appropriate baselines.   Perform structured error analysis: categorize failure modes (false positives, missed detections, localization errors, misclassifications) and break down performance by data slices (object size, occlusion, image quality).   Select and justify model architectures based on task requirements, latency, and accuracy tradeoffs.   Engineering and production   Develop production-grade Python libraries for the complete ML lifecycle.   Design and implement data pipelines including ingestion, preprocessing, annotation workflows, and quality monitoring.   Own experiment tracking and model versioning: configurations, random seeds, dataset versions, environment specs, and model checkpoints.   Build model serving pipelines that meet latency and throughput requirements.   Conduct thorough code reviews and write integration tests for ML pipelines.   Collaboration and craft   Share knowledge with teammates and contribute to best practices for model development, evaluation, deployment, and monitoring.   Advocate for and uphold software quality standards within the ML team.   Communicate research findings, technical decisions, and model limitations clearly to stakeholders and clients.     Qualifications & Experience 2-5 years of industry experience in computer vision and machine learning.   Solid understanding in  modern computer vision and deep neural networks, including:   Object detection   Semantic segmentation Image classification Vision transformers and foundation models Vision language models Similarity search     Experience taking at least one ML model into production and maintaining it there.   Experience selecting, fine-tuning, and adapting model architectures (CNNs, transformers, foundation models) for specific use cases.   Demonstrated ability to read ML research papers, extract the key ideas, and implement them.   Ability to debug training instabilities and conduct systematic error analysis.   Proficiency in Python and the core ML stack:   PyTorch and Lightning   OpenCV NumPy and pandas Scikit-Learn FastAPI and Pydantic   Strong software engineering practices, including: Git version control Unit and integration testing (Pytest) CI/CD pipelines (GitHub Actions) Docker and reproducible environments Experiment tracking and model versioning ML DevOps Python type hinting   Proven ability to own technical projects independently, from problem framing through production deployment.     Desired Additional Experience Multi-modal computer vision   Custom object detection model development   Generative models for data augmentation   Extracting measurements from GIS and/or drone-metadata-enriched imagery   Model quantization and latency optimization for edge deployment   Systematic hyperparameter tuning at scale   Energy, utilities, geospatial, or industrial inspection domains     Additional information: This position does not include sponsorship for United States work authorization.