Senior Computer Vision Engineer – Scalable Feature Engineering

Harbor Softworks

Contract · Remote · Flexible hours

About the role

Harbor Softworks is strengthening the security posture of its cloud‑hosted services. As a Computer Vision Engineer you will lead the vision‑based threat detection component of the Aegis Vision Guard module, integrating advanced CV pipelines into our security hardening initiative.

Key responsibilities

• Design and implement a real‑time object detection system using YOYOv8 to monitor unauthorized camera feeds in cloud environments.
• Develop secure data pipelines in AWS SageMaker, ensuring encrypted model storage and inference endpoints.
• Integrate CV models with existing security orchestration APIs, delivering JSON payloads via FastAPI.
• Benchmark model latency and accuracy, achieving sub‑100 ms inference on GPU‑accelerated instances.
• Write automated tests with PyTest and CI scripts in GitHub Actions to enforce security compliance.
• Document deployment procedures and hand over a reproducible Docker image for the Aegis Vision Guard service.

Must-have skills

• Deep expertise in Python computer‑vision libraries (OpenCV, PyTorch, TensorFlow).
• Experience building and securing cloud‑native ML pipelines on AWS or GCP.
• Proficiency with containerization (Docker) and orchestration (Kubernetes).
• Strong understanding of cryptographic best practices for model data.
• Ability to write clean, testable code and CI/CD configurations.

Nice to have

• Familiarity with edge‑device inference optimization.
• Background in cybersecurity incident response.