Senior Video AI Systems Engineer

Real-Time Video Streaming and AI Engineer end-to-end

🚨 We're Hiring: Senior Python Developer (6-8 years exp)

📍 Location: On-site Caesarea / Hybrid from Israel

📅 Start: Immediate – Quick onboarding

💼 Company: Argu

💰 Full-Time

About Argu:

Argu is the world’s first agentic video analysis platform, backed by the world’s leading investors. We turn cameras into an always-on operator that understands what’s happening, investigates incidents end-to-end, and delivers actionable outcomes in real time.

About the Role

We’re hiring a senior, hands-on engineer to own and build our real-time video AI application to own the product.

You will take ready computer vision and AI models and algo from R&D and turn them into a production-grade system that can handle hundreds of concurrent live streams on GPUs and edge devices.

You will be the technical owner of the application: architecture, performance, reliability, and scalability.

Responsibilities

• Own the end-to-end real-time video AI application and its architecture
• Build and operate large-scale video streaming pipelines (hundreds of concurrent streams)
• Design and optimize GStreamer and NVIDIA DeepStream pipelines
• Deploy and accelerate inference using CUDA, TensorRT, OpenCV, and PyTorch
• Optimize latency, throughput, memory usage, and GPU utilization (multi-stream concurrency)
• Deploy on NVIDIA GPU servers and Jetson platforms (edge inference)
• Build backend services and APIs (FastAPI) for control, orchestration, and integration
• Integrate embeddings workflows and vector similarity search
• Profile and debug production issues: dropped frames, GPU contention, memory leaks, bottlenecks
• Collaborate closely with R&D to productionize models and improve system performance

Requirements

• 6+ years of hands-on engineering experience
• Strong experience with real-time video systems and streaming at scale
• Practical experience with GStreamer (DeepStream is a major plus)
• Strong GPU acceleration experience with CUDA and TensorRT
• Production experience with OpenCV and PyTorch
• Experience deploying AI inference on NVIDIA GPUs and/or Jetson platforms
• Proven ability to handle multi-stream concurrency and performance tuning
• Strong Linux experience
• Docker deployment experience
• Backend engineering experience in Python, including FastAPI (or equivalent)
• Strong microservices architecture building experience
• Experience in distributed systems development / on-prem

Nice to Have

• GPU profiling and tuning (CUDA streams, kernel optimization)
• Vector databases and large-scale embeddings pipelines
• C++ in performance-critical components
• Experience with mission-critical or low-latency production systems

Most Important

• Team player
• The type of person we can have a beer with after work
• Knows startup enviroment