Production-Ready AI Surveillance Architecture
Summary
Freelancer Client is hiring: Production-Ready AI Surveillance Architecture.
Location: Remote
I am kicking off an AI-powered surveillance and face-recognition platform and want to start on solid ground. The goal is a clean, production-ready project structure that stitches together every piece of the stack so my team can focus on feature work rather than boilerplate.
Backend – Python 3.11, FastAPI, SQLAlchemy + Alembic, PostgreSQL, Redis, WebSocket
AI layer – YOLOv8 (people detection / counting), DeepSORT (tracking), RetinaFace + InsightFace-ArcFace (face detection / recognition), FAISS for vector search, OpenCV to pull RTSP streams
Frontend – Next.js 15 with TypeScript, Tailwind CSS, Recharts for dashboards
Infrastructure – Docker, docker-compose, NVIDIA CUDA runtime for GPU inference, Nginx reverse proxy
Skills: JavaScript, Python, Linux, Node.js, PostgreSQL, Redis, Docker, FastAPI
Budget: $12500–$37500 USD
Source: Freelancer Client via Remote / Online. Apply on the source website.
Original
I am kicking off an AI-powered surveillance and face-recognition platform and want to start on solid ground. The goal is a clean, production-ready project structure that stitches together every piece of the stack so my team can focus on feature work rather than boilerplate.
Tech stack that must come wired in:
• Backend – Python 3.11, FastAPI, SQLAlchemy + Alembic, PostgreSQL, Redis, WebSocket
• AI layer – YOLOv8 (people detection / counting), DeepSORT (tracking), RetinaFace + InsightFace-ArcFace (face detection / recognition), FAISS for vector search, OpenCV to pull RTSP streams
• Frontend – Next.js 15 with TypeScript, Tailwind CSS, Recharts for dashboards
• Infrastructure – Docker, docker-compose, NVIDIA CUDA runtime for GPU inference, Nginx reverse proxy
Backend reliability and performance sit at the top of the priority list, so I expect an asynchronous FastAPI setup, connection pooling, health checks, graceful shutdown, and clear separation between I/O-bound and GPU-bound tasks.
Deliverables should include:
1. Well-documented repo (or mono-repo) layout for backend, AI services, and frontend, each with local and container entry points.
2. Dockerfiles and a docker-compose.yml that bring up the full stack—database, Redis, GPU-enabled inference service, FastAPI app, Next.js front, and Nginx—behind sensible network aliases.
3. Example FastAPI routes (REST + WebSocket) illustrating stream ingestion and real-time event broadcast.
4. Stub pipelines that call YOLOv8, DeepSORT, RetinaFace, InsightFace, and FAISS in a non-blocking fashion, ready to be swapped with trained weights.
5. Automatic database migrations via Alembic and a seed script.
6. README with step-by-step setup, development workflow, and commands for running tests and linting.
When you respond, highlight experience delivering scalable FastAPI or similar systems, especially where GPU inference and real-time streaming were involved. I will review repo samples or links that prove you have assembled comparable architectures before.
Location & Details
Apply on source →About this listing
This remote opportunity was imported from Freelancer and is shown here for discovery. To apply, follow the link to the original posting.