AI Model System Software Performance Optimization Engineer - Senior Engineer

Overview

Senior Engineer role focused on optimizing AI and machine learning model performance and workflows for Windows on Snapdragon platforms. The role covers benchmarking, reference implementations, software-stack improvements, and developer support.

What you'll do

• Enable AI application development through the Snapdragon software stack.
• Resolve complex customer issues and reduce barriers to Windows AI adoption.
• Benchmark AI tools, workflows, and models across competing platforms.
• Improve AI model performance, efficiency, and accuracy on Snapdragon platforms.
• Develop optimization workflows for Snapdragon CPUs, GPUs, and NPUs.
• Analyze trends in machine learning, generative AI, and large language models.
• Collaborate with architects, development leads, customer engineers, and application developers.

What you'll need

• 3–5 years of experience in AI/ML application development.
• Experience optimizing AI models for performance, power, and accuracy on CPUs, GPUs, or NPUs.
• Experience designing software frameworks for heterogeneous or multiprocessor systems.
• Proficiency with PyTorch, TensorFlow, ONNX Runtime, and MLIR.
• Strong programming skills in C, C++, and Python.
• Knowledge of CNNs, RNNs, Transformers, ensemble methods, and transformer models.
• At least 2 years of programming experience for bachelor's degree holders, or equivalent master's/PhD qualification paths.

Nice to have

• Familiarity with open-source inference frameworks such as llama.cpp.
• Experience developing, optimizing, or deploying LLMs or foundation models.
• Familiarity with embedding models, sentence transformers, retrieval pipelines, and production AI workflows.
• Experience with processor-specific optimization and profiling tools.

Details

• Location: Bangalore, India.