Design, develop, and deploy Edge AI solutions for real-world applications.
Optimize Generative AI models (LLMs, Diffusion Models, etc.) for edge deployment (e.g., pruning, quantization, distillation).
Implement embedded software solutions (C/C++,Python,RTOS) to integrate AI models into edge devices(IoT, drones, robotics, etc.).
Collaborate with global teams (US,EU,APAC) to align AI solutions with business needs.
Research and prototypenovel Edge AI techniques (federated learning, on-device ML, tinyML).
Document and present technical findings to stakeholders
Requirements
Education: Bachelor’s/Master’ sin ComputerScience,ElectricalEngineering, or related field.
Experience: 5+years in AI/ML engineering, with at least 2 years in Edge AI or embedded AI.
Technical Skills
Strong expertise in GenerativeAI (LLMs,GANs,VAEs)and model optimization.
Hands-on experience with edge frameworks (Tensor Flow Lite, ONNX Runtime,PyTorchMobile).
Proficient in embedded programming (C/C++,Python,Rust)and edge platforms (NVIDIAJ etson, RaspberryPi, Qualcomm Snapdragon).
Familiarity with ML Ops for edge (model deployment, OTA updates)
Excellent English communication (written&verbal) for global collaboration.
Ability to work incross-functional, distributed teams.