Description
The role focuses on benchmarking and evaluating Kinara AI products by collaborating with technical marketing, product, and customer support teams; exploring benchmarking methods and tools for vision and LLM/VLM models; writing and optimizing Python and C/C++ scripts for deep-learning model deployment; and preparing analysis reports. Responsibilities include measuring latency, throughput, accuracy, and power consumption, using MLPerf and MLFlow, and evaluating LLM benchmarks. The posting requires a BTech in ECE/CS, 4+ years of experience in machine learning or a related field, and experience with neural networks, AI/ML/DL models, TensorFlow, Caffe, PyTorch, C++ and Python workload flows, and hardware and software performance evaluation.
