Description
The Role
We are seeking an experienced Edge AI/CV Orchestration Engineer to enhance and scale our core engine that manages AI workloads on resource-constrained edge devices.
Your primary mission is to improve the "brain" of our system: the orchestration engine that decides which AI tasks run, when they run, and how they perform on hardware like the NVIDIA Jetson Orin Nano. You will be the bridge between our backend infrastructure and our deployed physical hardware, ensuring our edge devices operate efficiently, reliably, and at scale.
Requirements
Required Qualifications (Must-Haves)
- Proven Experience: 3-5+ years of experience in backend development, systems programming, or DevOps, with a focus on distributed or embedded systems.
- Expert Python: Strong proficiency in Python, especially for building backend services, asynchronous programming (e.g., asyncio), and system-level scripting.
- NVIDIA Jetson Expertise: Demonstrable, hands-on experience working with the NVIDIA Jetson platform (e.g., Orin Nano, Xavier NX, AGX). You should be comfortable with the JetPack SDK and its tools.
- Deep Linux Knowledge: Strong command of the Linux operating system. You must understand system administration, process management, shell scripting, networking, and performance tuning (e.g., using top, htop, perf).
- Backend Systems: Solid experience designing, building, and maintaining APIs and microservices.
⭐ Preferred Qualifications (Nice-to-Haves)
- Containerization: Experience with Docker, containerd, and/or edge-focused Kubernetes (K3s, MicroK8s).
- NVIDIA Stack: Direct experience with the NVIDIA stack is a major plus, especially NVIDIA DeepStream, TensorRT, or Triton Inference Server.
- AI/CV Exposure: A good understanding of the challenges in deploying computer vision or machine learning models.
- Other Languages: Experience with C++ or Go for performance-critical components.
- Fleet Management: Experience with IoT fleet management tools (e.g., AWS IoT Greengrass, Azure IoT Edge, or Balena).
Roles And Responsibilities
Key Responsibilities
- Engine Enhancement: Design, develop, and optimize new features for our Python-based backend orchestration engine.
- System Management: Implement robust solutions for resource allocation (CPU, GPU, memory), task scheduling, and priority management across a fleet of edge devices.
- Performance Optimization: Profile and fine-tune the performance of AI/CV pipelines on the Jetson platform, diving deep into the Linux environment to resolve bottlenecks.
- Backend & API Development: Build and maintain scalable backend services and APIs (e.g., REST, gRPC) that allow for remote deployment, monitoring, and updating of tasks.
- Deployment & CI/CD: Improve automated deployment pipelines for pushing new AI models and orchestration logic to devices in the field.
- Troubleshooting: Act as the key troubleshooter for complex system-level issues that span AI models, our orchestration code, and the underlying Linux OS on the Jetson hardware.