AI Engineer – Model Optimisation & Acceleration, AMD

AI Engineer
India, Bengaluru
October 13, 2026
Full Time

Apply for this job

Email *
Executive Name *

Job Description

AMD is looking for a candidate who can work as an AI engineer in Bangalore who can help optimize, enhance, and run the machine learning models on the CPU, GPU, and NPU architecture. This job includes model optimization, production of AI models, quantization and compression, and efficient inference. The areas covered include generative AI, computer vision, multimodal, and speech models in robotics, healthcare, and automotive sectors.

Location: Bangalore, India

Qualification: Bachelor’s Degree/Master’s Degree (Preferred)

Experience: Experience with GPU/hardware acceleration 

Apply: Click Here

Responsibilities

  • Optimise generative, vision, multimodal, and speech models for efficient deployment across diverse production environments.
  • Port machine learning models efficiently across PyTorch, ONNX, and compatible runtime frameworks for deployment.
  • Run models on GPU and NPU hardware accelerators for a marked increase in performance.
  • Reduce inference latency, increase throughput, improve memory optimization, and utilize batching and caching.
  • Apply quantisation, model compression, profiling, and debugging techniques to enhance overall system performance.

Requirements

  • Demonstrate strong proficiency in PyTorch or comparable machine learning frameworks for professional development.
  • Utilize knowledge of ONNX or similar frameworks to implement effective model deployment pipelines.
  • Be knowledgeable in using Python and C++ programming languages for the purpose of developing artificial intelligence applications.
  • Implement knowledge of GPU-acceleration technologies like CUDA, ROCm or similar.
  • Demonstrate understanding of transformers, CNNs, optimisation, quantisation, and performance tuning techniques in practice.

Preferred Qualifications

  • Leverage experience of deploying edge AI or embedded machine learning environments in production.
  • Build generative AI or multimodal AI systems for actual use cases in production.
  • Be familiar with distributed inference and real-time streaming systems for scalable deployment of AI systems.
  • Apply model compression and lower-precision computing techniques to improve deployment efficiency and performance.
  • Optimise workloads across heterogeneous CPU, GPU, and NPU platforms for demanding production environments.

Related Jobs