ML Performance Optimization Engineer - 42dot

Key Responsibilities

• Optimize AI models for GPU and NPU execution, reducing inference latency and power consumption in vehicle hardware.
• Collaborate with AI Model and Software teams to validate performance gains and ensure model stability across diverse driving scenarios.
• Develop and maintain automated profiling pipelines to capture system metrics, identify bottlenecks, and generate actionable insights.
• Implement performance analysis tools and scripts to benchmark model variants and document results for continuous improvement.
• Contribute to the deployment strategy of optimized models, ensuring seamless integration with the autonomous driving stack.

Requirements

• Strong experience with GPU and NPU optimization techniques for deep learning models.
• Proficiency in performance profiling tools (e.g., Nsight, TensorRT, or equivalent) and scripting languages such as Python.
• Solid understanding of autonomous driving AI pipelines and real‑time inference constraints.
• Excellent analytical skills and ability to translate profiling data into concrete optimization actions.
• Effective communication skills for cross‑functional collaboration.