Full Stack Engineer (Edge Deployment Focus)

Roboflow (Headquarters: Remote, SF, NYC)

full stack edge computing iot computer vision ai ml deployment inference python docker kubernetes nvidia jetson luxonis oak raspberry pi model optimization sdk open source saas developer tools AI Engineer Full Stack Engineer

**Company:** Roboflow provides end-to-end tools for computer vision, from data to deployment. We're Series B funded by GV and empower over 1M developers. Our open source Inference server is key to edge deployment.

**Role:** This Full Stack Engineer role specializes in building and enhancing Roboflow's capabilities for deploying computer vision models to edge devices. You'll work on our Inference server, device management features, SDKs, and integrations to make edge deployment seamless for our users.

**Responsibilities:**
*   Develop features for Roboflow Inference (open source) and related cloud management tools.
*   Improve support for various edge hardware (NVIDIA Jetson, Luxonis OAK, Raspberry Pi, mobile devices, etc.).
*   Build and maintain SDKs for interacting with edge deployments.
*   Optimize models and inference pipelines for performance on resource-constrained devices.
*   Work on the full stack, including backend services, APIs, and potentially front-end interfaces related to edge management.
*   Collaborate with hardware partners and the open-source community.

**Ideal Candidate:**
*   Strong full-stack engineering background (Python, JavaScript, React, etc.).
*   Experience with edge computing concepts, challenges, and technologies.
*   Familiarity with deploying ML/CV models, especially on devices like Jetson, OAK, Coral, or mobile platforms.
*   Experience with Docker, Kubernetes, and cloud infrastructure (AWS, GCP, Azure).
*   Understanding of model optimization techniques (e.g., quantization, pruning) is a plus.
*   Experience with networking protocols relevant to edge devices (e.g., MQTT, RTSP) is beneficial.
*   Strong problem-solving skills and ability to work autonomously.