Binariks is seeking an experienced engineer with a strong background working with NVIDIA technologies. The ideal candidate will have hands-on experience in one or more areas.
What We’re Looking For * Strong Python & AI/ML background (PyTorch/TensorFlow). * Experience optimizing models with TensorRT or similar NVIDIA inference tools. * Familiarity with GPU-accelerated cloud AI (AWS/GCP/Azure with NVIDIA GPUs). * Understanding of ML model deployment (Docker, ONNX, Triton).
Will be a plus * Experience with NVIDIA RAPIDS (GPU-accelerated data science). * Knowledge of distributed training (multi-GPU, Horovod).
Your responsibilities * Developing and optimizing AI/ML models for NVIDIA GPUs (training & inference). * Working with NVIDIA-accelerated frameworks (TensorRT, RAPIDS, cuDNN, Triton Inference Server). * Deploying high-performance AI models on NVIDIA hardware (GPUs, Jetson, DGX). * Improving model efficiency (quantization, pruning, mixed-precision training). * Implementing MLOps pipelines for GPU-accelerated AI workloads.