Computer Vision Engineer

Koireader Technologies; United States; A distancia; USD 120.000 - 170.000; Jornada completa

Ventajas ofrecidas por este puesto de trabajo

Meritocracy

NVIDIA hardware access

Autonomy in experimentation

Cutting-edge Generative AI tools

Descripción de la vacante

Koireader Technologies seeks a Systems-First Computer Vision Engineer to push live video AI into production with real-time pipelines built on GStreamer/RTSP. The role focuses on ultra-low latency inference across Edge (NVIDIA Jetson) and Cloud environments, integrating models into robust streaming systems.

You will maintain a modular Python framework, optimize performance, and ensure fault tolerance even when cameras go offline or frames are dropped.

Formación

• Deep expertise in video streaming protocols (RTSP, WebRTC) and processing tools.
• Experience with OpenCV and image processing fundamentals; geometry and color spaces.

Responsabilidades

• Architect streaming pipelines for real-time video ingestion with multiple RTSP streams.
• Integrate trained models into production pipelines ensuring stability and low latency.
• Latency optimization across Edge devices (NVIDIA Jetson) and Cloud servers.
• Build fault-tolerant systems that recover from camera outages or dropped frames.
• Maintain and evolve a modular, efficient Python codebase for the vision framework.
• Diagnose bottlenecks across CPU, GPU, and network and implement fixes.

Conocimientos

Video streaming expertise

Core vision stack

Production Python

Docker deployment

Math & statistics

Herramientas

GStreamer

FFmpeg

WebRTC

TensorRT

DeepStream

Triton Inference Server

PyTorch

TensorFlow

Kubernetes

Descripción del empleo

Summary

We are looking for a Systems-First Computer Vision Engineer who specializes in the \"Last Mile\" of AI: taking a model and making it run continuously, reliably, and instantly on live video feeds. This role is not about training models in a notebook; it is about building the high-performance highways (Pipelines) that allow Vision AI to run in the real world. You will architect robust streaming architectures using GStreamer/RTSP and optimize inference for ultra-low latency on Edge and Cloud environments.

Key Responsibilities

Architect Streaming Pipelines: Design and implement robust, real-time video ingestion pipelines handling multiple RTSP streams using tools like GStreamer, FFmpeg, and WebRTC.

Inference Integration: Take trained models from the ML team and integrate them into production pipelines. Your goal is to ensure the model runs stable, fast, and without memory leaks.

Latency Optimization: Obsess over milliseconds. Optimize data processing pipelines to ensure low-latency inference on both Edge devices (NVIDIA Jetson) and Cloud servers.

Fault Tolerance: Build "Crash-Proof" systems. Ensure that if a camera goes offline or a frame is dropped, the system recovers gracefully without manual intervention.

Framework Evolution: Maintain and evolve our proprietary vision framework by writing modular, reusable, and efficient Python code/libraries.

Performance Engineering: Diagnose bottlenecks in the system whether it's CPU, GPU, or Network and implement architectural fixes.

Skills & Requirements

Video Engineering Mastery: Deep expertise in video streaming protocols (RTSP, WebRTC, FastRTC) and processing tools (FFmpeg, GStreamer). You know how to handle frame buffers, decoding, and encoding efficiently.

Core Vision Stack: extensive experience with OpenCV and Image Processing fundamentals. You understand geometry, color spaces, and pixel-level manipulation.

Production Python: Strong experience writing fault-tolerant, multi-threaded/async code. You understand how to manage resources in long-running processes.

Deployment Native: Hands-on experience with Docker is mandatory. You know how to containerize a complex vision application with all its dependencies.

Mathematical Foundation: Command over geometry and statistics for designing complex logic layers on top of model detections.

Brownie Points

Hardware Acceleration: Experience with NVIDIA TensorRT, DeepStream, or Triton Inference Server for maximizing GPU throughput.

Framework Knowledge: Familiarity with PyTorch/TensorFlow runtimes (strictly for inference and loading models).

DevOps Awareness: Understanding of Kubernetes orchestration and CI/CD pipelines.

Data Handling: Experience with SQL/NoSQL databases for storing metadata and analytics results.

What We Offer

Meritocracy: A candid startup culture where the best ideas win.

The Playground: Access to the latest NVIDIA Hardware and cutting-edge Generative AI tools.

Ownership: Lead a performance-oriented team driven by autonomy and open to experiments.

Impact: Design systems for high accuracy and scalability that physically move the global supply chain.