Description

You will own the optimization and deployment of AI models on embedded platforms and FPGAs.

This role is on-site.

Responsibilities

• Develop and optimize AI model inference pipelines for embedded systems.
• Integrate AI compilers (TVM, TensorRT, XLA, Glow, OpenVINO) into the software stack.
• Implement quantization techniques and evaluate accuracy-performance tradeoffs.
• Profile and benchmark AI models on embedded boards to resolve performance bottlenecks.
• Collaborate with engineering teams to support continuous runtime optimization.

Required Skills

• 4+ years of experience in Embedded AI, AI Compiler, or AI Runtime Engineering.
• Strong proficiency in C, C++, Python, and Shell Scripting.
• Deep understanding of AI inference flow from model compilation to runtime execution.
• Hands-on experience with AI compilers such as TVM, TensorRT, XLA, Glow, or OpenVINO.
• Experience with quantization and inference optimization techniques.
• Knowledge of ONNX, PyTorch, and TensorFlow inference export pipelines.
• Hands-on experience with embedded boards or FPGA platforms.

Preferred Skills

• Strong analytical, debugging, and performance optimization skills.
• Ability to maintain technical documentation and support cross-functional development.

Key Skills

Education

Any Graduate