Overview:
We are looking for a hands-on senior engineer to own the end-to-end productionization of Real-Time video systems and AI pipelines.
This role is not research and not model invention.
You will take existing computer vision models and algorithmics and integrate them into production, turning them into high-performance, scalable, production-grade systems running across hundreds of concurrent video streams on GPU and edge hardware.
You will work at the intersection of:
Python microservices backend development
video streaming using GStreamer and NVIDIA DeepStream
Distributed and multithreaded development
Real-Time inference
AI pipeline/processing optimization
Deploy and accelerate CV and AI models using CUDA, TensorRT, PyTorch, OpenCV
This is a deeply engineering-focused role with real ownership.
Requirements: Required Experience
5+ years of hands-on Python backend /architecture engineering for large-scale/distributed systems
Docker + Linux, production debugging
Background in Real-Time video streaming (RTSP, FFMPEG, HLS, WEBRTC)
Practical experience with GStreamer
Experience with Nvidia CUDA
Production use of TensorRT and/or DeepStream
Solid experience with OpenCV and PyTorch
Experience scaling AI inference
Strong Linux experience
This position is open to all candidates.