AI Model Optimizer

We are seeking a highly motivated AI Model Optimizer (Fresher) to help improve the efficiency and performance of machine learning models. This role focuses on compressing, quantizing, pruning, and accelerating ML models to run efficiently on various platforms including cloud, mobile, and edge devices. You'll work with data scientists, ML engineers, and MLOps teams to fine-tune deep learning models for real-world deployment. Responsibilities: Work on optimizing deep learning models for performance, inference speed, and memory efficiency. Implement model compression techniques like quantization, pruning, and knowledge distillation. Collaborate with AI researchers and engineers to benchmark models across different hardware (CPU, GPU, TPU, Edge devices). Utilize tools like TensorRT, ONNX, OpenVINO, and TensorFlow Lite for model conversion and deployment. Profile models to identify bottlenecks and enhance execution using compiler-level optimizations. Support integration of optimized models into production environments and pipelines. Document experiments, performance metrics, and optimization trade-offs clearly for reproducibility. Requirements: Bachelor's degree in Computer Science, Electronics, or related technical field. Strong foundation in machine learning/deep learning concepts and popular libraries (TensorFlow, PyTorch, Scikit-learn). Familiarity with model optimization frameworks like ONNX, TensorRT, or OpenVINO. Understanding of matrix operations, floating-point arithmetic, and numerical precision. Basic experience with Python, NumPy, and ML deployment tools. Good problem-solving skills and a detail-oriented mindset. Bonus: Exposure to AI on edge devices, low-latency models, or compiler toolchains like TVM or XLA.