Senior Computer Vision Engineer for ML Model Integration Delivery

NexGen Media

Contract · Remote · Flexible hours

About the role

NexGen Media is revamping its legacy video processing pipeline, codenamed "VisionForge", to achieve true zero‑downtime deployments. As a Senior Computer Vision Engineer you will lead the integration of modern CV models into this platform while preserving uninterrupted service for millions of daily users.

Key responsibilities

• Design and implement a streaming inference service using TensorRT and NVIDIA Triton for real‑time object detection.
• Migrate existing OpenCV‑based modules to PyTorch Lightning pipelines, ensuring compatibility with the existing CI/CD flow.
• Develop blue‑green deployment scripts with Kubernetes and ArgoCD to meet zero‑downtime SLAs.
• Create automated validation suites that compare legacy output with new model predictions across 10,000+ test videos.
• Collaborate with DevOps to instrument Prometheus metrics for latency and throughput monitoring.
• Document the VisionForge architecture and hand over knowledge to the on‑call team.

Must-have skills

• Deep expertise in Python, OpenCV, PyTorch, and TensorRT.
• Proven experience building high‑throughput CV pipelines on Kubernetes.
• Strong understanding of zero‑downtime deployment patterns (blue‑green, canary).
• Ability to write performant C++ extensions when needed.
• Solid grasp of CI/CD tools such as GitHub Actions or Jenkins.

Nice to have

• Experience with MLOps platforms like MLflow or Kubeflow.
• Familiarity with video codecs and streaming protocols (RTSP, HLS).