US Citizenship with ability to pass a federal background check.
Bachelor's degree in Computer Science, Data Science, Software Engineering, or related field.
5-7 years of software engineering or data science experience.
4+ years of hands-on experience with Computer Vision models.
Proficient in Python and core machine learning libraries (NumPy, Pandas, Scikit-Learn).
Experience with PyTorch or TensorFlow for neural network training.
Hands-on experience implementing YOLO for object detection.
Responsibilities
Train, fine-tune, and evaluate YOLO object-detection models on proprietary datasets.
Process and clean raw video files into high-quality training datasets.
Manage the data annotation lifecycle, ensuring quality and generating synthetic data as needed.
Develop inference pipelines using Python to parse video frames and export structured prediction data.
Generate performance reports and metrics to identify model blind spots and improve detection capabilities.
Collaborate in an Agile/Scrum framework with the Senior AI/ML Lead and other engineers to deliver production-ready code.
Benefits
Hybrid work schedule (1-2 days/week).
Opportunity to work on cutting-edge AI/ML projects for federal clients.
Collaborative team environment with a focus on Agile methodologies.
Hands-on experience with advanced computer vision technologies.
Full Job Description
Niyam is seeking an experienced AI/ML Computer Vision Engineer to support one of our federal clients. As a Mid-Level AI/ML Engineer on our Computer Vision team, you will work within a specialized 3-person pod dedicated to building custom object detection and classification models using the YOLO framework. Your mission will be to process live and recorded Full-Motion Video (FMV) feeds, enabling automated parsing of entities like roads, vehicles, people, and terrain features. You will play a hands-on role in bringing raw production video into our secure training environment, curating datasets, training models, and deploying high-performance inference pipelines.
Roles and Responsibilities
Model Training & Experimentation: Train, fine-tune, and evaluate custom YOLO object-detection models on proprietary datasets. Run experiments with different hyperparameters, augmentations, and model sizes to find the optimal balance of speed and accuracy.
Data Engineering & Ingestion: Process, clean, and format raw video files recorded from production environments into high-quality datasets for training.
Dataset Annotation & Curation: Manage the data annotation lifecycle, labeling images and video frames, verifying annotation quality, and generating synthetic data where needed.
Inference Pipeline Development: Write Python scripts to parse video frames, feed them into inference engines, and export structured prediction data (JSON/Protobuf) representing detected objects.
Model Evaluation: Generate performance reports, confusion matrices, and precision-recall curves to identify model blind spots and continuously improve detection capabilities.
Collaborative Agile Delivery: Work closely with the Senior AI/ML Lead, video engineers, and developers in an Agile/Scrum framework to deliver production-ready code in short sprints.
Qualifications and Education Requirements
US Citizenship with ability to successfully complete a federal background investigation.
Bachelor's degree in Computer Science, Data Science, Software Engineering, or a related discipline.
5-7 years of software engineering or data science experience.
4+ years of hands-on experience building/training Computer Vision models.
Programming in Python and using core machine learning libraries (NumPy, Pandas, Scikit-Learn).
Hands-on experience with PyTorch or TensorFlow for training neural networks.
Experience implementing YOLO (e.g., YOLOv8/v9) for object detection, segmentation, or classification.
Familiarity with image and video processing techniques using OpenCV or FFmpeg.
Data curation, formatting, and experience using data annotation platforms (e.g., CVAT, LabelImg).
Using Git for version control and collaborating on shared codebases.
Strong analytical skills, with a focus on benchmarking model performance (mAP, FPS, inference latency).
Ability to work a hybrid schedule 1-2 days/week.
Preferred Skills
Familiarity with containerized development environments (Docker).
Experience with GPU execution environments and model export formats (ONNX, TensorRT).
Experience with multi-object tracking libraries.
Familiarity with Agile tools like Jira and Confluence.