AI Engineer - Computer Vision

Detect•Miami, FL

5d•Onsite

About The Position

At Detect, we’re redefining how organizations see and respond to the world around them. Our mission is to turn complex data into clear, actionable insights that drive smarter decisions. We build cutting-edge solutions that fuse technology, geospatial intelligence, and automation to solve real-world challenges — from infrastructure management and public safety to climate resilience and beyond. As a fast-growing, innovation-driven company, we’re always looking for passionate and curious people to join our team. We value creativity, collaboration, and a commitment to excellence. At Detect, you’ll work on impactful projects, use the latest tools and technologies, and help shape the future of intelligent systems. Whether you’re building software, analyzing data, or designing user experiences, you’ll find your place here. Why Join Us? Growth: With a strong emphasis on personal development, we encourage continuous learning and tackling challenging projects that contribute to your professional growth. Impact: Play a pivotal role in shaping the future of our technology and products, directly influencing the success of our solutions. Culture of experimentation: We live by the mantra “fail fast, fail often”. By encouraging experimentation and learning from each failure, we pave the way for significant breakthroughs. We promote an environment where every team member is empowered to test new ideas, challenge the status quo and contribute to a culture of continuous innovation.

Requirements

Experience building and deploying machine learning or computer vision solutions in real-world environments (production systems, customer-facing products, or internal platforms). Demonstrated experience through internships, research, or substantial projects is acceptable.
Strong foundation in computer vision and deep learning, with hands-on experience in areas such as object detection, semantic segmentation, or image classification.
Proficiency in Python and practical experience with deep learning frameworks such as Pytorch or Tensorflow
Experience working with end-to-end ML workflows, including data preprocessing, model training, evaluation, and iteration.
Comfortable working in ambiguous problem spaces and translating real-world constraints into technical solutions.
Strong communication skills and the ability to collaborate effectively with engineers, product, and operational teams

Nice To Haves

Experience deploying or supporting ML models in production (e.g., APIs, batch inference pipelines, edge deployment, or cloud-based systems).
Hands-on experience with MLOps tooling such as MLflow, Weights & Biases, DVC, or similar experiment tracking and lifecycle tools.
Familiarity with cloud platforms (GCP, AWS, or Azure) and containerized workflows (Docker).
Experience with large-scale or high-resolution imagery, including aerial, satellite, or infrastructure inspection data.
Experience improving model performance through data-centric approaches (dataset curation, labeling strategies, augmentation).

Responsibilities

Experiment with and prototype computer vision models: Design, train, and evaluate deep learning models for object detection, segmentation and classification on real-world infrastructure imagery.
Support MLOps and data pipelines: Collaborate with the team to improve data preprocessing pipelines, model evaluation tools, and ML lifecycle tracking systems using tools like MLflow.
Perform error analysis and quality improvements: Analyze failure modes in models and datasets, and contribute to strategies for improving performance across edge cases.
Explore and test state-of-the-art vision architectures including transformer-based vision models (e.g. ViTs, DINOv2, SAM3).
Gain hands-on experience in taking AI models from experimentation to deployment, including learning about dataset versioning, reproducibility, and model performance monitoring in production-like environments.