AI Model Optimization Scientist - Low-Latency Vision

A*STAR - Agency for Science, Technology and Research; Singapore; On-site; SGD 80,000 - 120,000; Full time

Job summary

A*STAR - Agency for Science, Technology and Research in Singapore is seeking an expert to lead research into optimization techniques for AI deployment. The ideal candidate will have a Ph.D. and extensive experience with AI inference engines and model compression techniques. Responsibilities include designing scalable architectures for high-throughput data streams and conducting co-design to optimize models for specific hardware. Join a cutting-edge team to advance high-performance AI solutions.

Qualifications

• Ph.D. in a related field with a focus on High-Performance AI.
• Deep understanding of AI Inference Engines like TensorRT and ONNX Runtime.
• Mastery of Model Compression techniques including Pruning and Quantization.

Responsibilities

• Lead research into optimization techniques to minimize latency.
• Design scalable AI deployment architectures for high-resolution data streams.
• Conduct hardware-software co-design for optimized model deployment.

Skills

C++

Python

Model Compression

AI Inference Engines

Parallel Computing

High-Performance AI

Education

Ph.D. in Computer Engineering, Computer Science, or Electrical Engineering

Job description

A*STAR - Agency for Science, Technology and Research in Singapore is seeking an expert to lead research into optimization techniques for AI deployment. The ideal candidate will have a Ph.D. and extensive experience with AI inference engines and model compression techniques. Responsibilities include designing scalable architectures for high-throughput data streams and conducting co-design to optimize models for specific hardware. Join a cutting-edge team to advance high-performance AI solutions.