AIML, Python with Linux

Role & responsibilities

• Strong proficiency in C, C++, Python, and shell scripting.
• Deep understanding of AI model inference flow from model compilation to runtime execution with embedded software stack.
• Familiarity with any AI compiler(e.g., TVM, TensorRT, XLA, Glow, OpenVINO).
• Familiarity with quantization and accuracy-performance tradeoffs.
• Experience working on AI deployment stacks.
• Experience debugging performance issues across compiler, runtime, and model levels.
• Knowledge of ONNX, PyTorch, or TensorFlow inference export pipelines.
• Hands-on experience running and profiling models on embedded boards or FPGA platforms.

Strong analytical skills to correlate performance data with model and runtime behavior.