Description

You will define and build end-to-end Edge AI systems, covering data acquisition, preprocessing, model execution, orchestration, and edge-cloud integration.

This role is on-site.

Responsibilities

• Architect solutions using NVIDIA Jetson, Intel OpenVINO, Qualcomm AI Engine, or ARM Ethos.
• Design and implement decentralized multi-agent architectures using Google ADK and LangGraph.
• Implement Agent-to-Agent (A2A) communication protocols for heterogeneous agent collaboration.
• Optimize models for deployment on resource-constrained edge devices using PTQ, QAT, and weight pruning.

Required Skills

• 8+ years of professional experience in Edge AI architecture and deployment.
• Hands-on experience with Retrieval-Augmented Generation (RAG) systems.
• Proficiency with LangChain and LangGraph for multi-agent orchestration.
• Experience with hardware accelerators (GPU, NPU, DSP, TPU, or VPU).
• Deep knowledge of TensorFlow and PyTorch, including model optimization techniques.
• Strong programming skills in C/C++ and Python.
• Experience with embedded Linux and Android-based AI deployments.

Key Skills

Education

Any Graduate