This role spans three practical execution areas:
Computer Vision & Image Analytics
You will implement and operate image analytics pipelines that support facial matching, object detection, scene understanding, and image similarity. This includes image preprocessing, feature extraction, model inference, evaluation, and performance optimization to meet mission-grade accuracy and latency requirements.
Geospatial & Location Inference from Imagery
You will contribute to capabilities that infer location, context, or environmental attributes from imagery—leveraging visual cues, metadata, and learned representations. This includes supporting image-based geolocation, landmark recognition, and contextual scene analysis used in intelligence workflows.
Multi-Modal AI & Image Search
You will support multimodal AI systems that combine vision models with LLMs, embeddings, and retrieval pipelines to enable natural-language search and reasoning over images and image collections. You will help integrate visual understanding into broader intelligence applications and workflows.
- Build and maintain computer vision pipelines for image ingestion, preprocessing, inference, and evaluation.
- Implement facial matching, and identity-related vision workflows in accordance with accuracy, safety, and compliance requirements.
- Develop and support object detection, image similarity, and scene understanding models.
- Contribute to image-based geolocation and location inference capabilities using visual features and contextual signals.
- Support multimodal AI workflows that combine image embeddings with LLM-based search and reasoning.
- Write clean, maintainable Python code and contribute to production services and APIs.
- Assist with model evaluation, bias testing, and accuracy monitoring for vision systems.
- Optimize inference pipelines for performance, scalability, and cost efficiency (GPU usage, batching, model selection).
- Collaborate with Product and Engineering teams to integrate vision capabilities into user-facing intelligence applications.
Required
- 3+ years of experience in computer vision, image processing, or applied machine learning.
- Hands-on experience with computer vision models and techniques (e.g., CNNs, transformers for vision, feature embeddings).
- Experience building or integrating image analytics such as facial recognition, object detection, or image similarity.
- Strong programming skills in Python ; experience with common CV/ML libraries (PyTorch, TensorFlow, OpenCV, etc.).
- Solid understanding of machine learning fundamentals, model evaluation, and performance tradeoffs.
- Experience working with large image datasets and production ML pipelines.
- Ability to work collaboratively in a fast-moving, mission-driven engineering environment.
Preferred
- Experience with facial matching or biometric systems in regulated or high-stakes environments.
- Experience with image-based geolocation or scene/location inference.
- Familiarity with multimodal AI systems , including combining vision models with LLMs or natural-language search.
Education:
- Bachelor’s degree in Computer Science, Engineering, Data Science, or a related technical field required.
Advanced degree is a plus but not required.