AI/Video Streaming Debugging & Optimization Expert
Budget: ₹12,500 – ₹37,500 INR
Job Title: Senior AI/Video Streaming Expert (Debugging & Optimization) – Airco Secure
Project Overview:
Airco Secure is an AI-powered surveillance platform with real-time video analytics, face recognition, and operational automation.
Important: Most of the system is already built.
We are currently facing 3–4 critical technical issues in our pipeline and are looking for an expert who can debug, optimize, and stabilize the system.
What We Need:
We are NOT looking for a beginner or someone to build from scratch.
We need someone who can quickly understand an existing system and fix complex issues.
Current Tech Stack:
RTSP streaming pipelines
NVIDIA DeepStream
Triton Inference Server
Savant pipeline
YOLO / custom models
AWS (GPU instances)
Backend + dashboard already developed
Key Responsibilities:
Debug and fix RTSP streaming issues (lag, frame drops, instability)
Optimize FPS and reduce latency in video pipeline
Resolve issues in DeepStream + Triton integration
Debug Savant pipeline performance bottlenecks
Fix model inference delays or incorrect detections
Improve GPU utilization and system performance
Ensure stable multi-camera processing (50+ feeds)
Ideal Candidate:
Strong hands-on experience with:
DeepStream
Triton
RTSP / GStreamer pipelines
Savant
Experience debugging real-time AI video systems
Ability to quickly identify and fix bottlenecks
Strong problem-solving mindset (very important)
Project Overview:
Airco Secure is an AI-powered surveillance platform with real-time video analytics, face recognition, and operational automation.
Important: Most of the system is already built.
We are currently facing 3–4 critical technical issues in our pipeline and are looking for an expert who can debug, optimize, and stabilize the system.
What We Need:
We are NOT looking for a beginner or someone to build from scratch.
We need someone who can quickly understand an existing system and fix complex issues.
Current Tech Stack:
RTSP streaming pipelines
NVIDIA DeepStream
Triton Inference Server
Savant pipeline
YOLO / custom models
AWS (GPU instances)
Backend + dashboard already developed
Key Responsibilities:
Debug and fix RTSP streaming issues (lag, frame drops, instability)
Optimize FPS and reduce latency in video pipeline
Resolve issues in DeepStream + Triton integration
Debug Savant pipeline performance bottlenecks
Fix model inference delays or incorrect detections
Improve GPU utilization and system performance
Ensure stable multi-camera processing (50+ feeds)
Ideal Candidate:
Strong hands-on experience with:
DeepStream
Triton
RTSP / GStreamer pipelines
Savant
Experience debugging real-time AI video systems
Ability to quickly identify and fix bottlenecks
Strong problem-solving mindset (very important)