Edge AI ML Engineer - Toolchain & ML Optimization

OmniVision Technologies Singapore Pte Ltd; Singapore; On-site; SGD 180,000 - 300,000; Full time

Job summary

OmniVision Technologies Singapore Pte Ltd in Singapore seeks a senior ML engineer to drive applied research for the NDK roadmap, focusing on quantization, pruning, distillation, and on-device inference within Edge AI compute solutions.

You will bridge the AI Architecture and Software (Edge AI) teams, prototype ML algorithms, benchmark performance, and translate hardware constraints into software requirements while engaging with the global edge AI community.

Qualifications

• Bachelor's or Master's in Computer Science, Electrical Engineering, Computer Engineering, or related field; PhD preferred in ML/optimization or computer architecture.
• 8+ years of experience in applied machine learning engineering or Edge AI software, with focus on model optimization, ML compilers, or on-device inference toolchain development.
• Proven expertise in quantization (PTQ, QAT), pruning, knowledge distillation, and model compression techniques.
• Strong knowledge of AI/ML algorithms, neural networks, and trade-offs between accuracy, compute, and memory.
• Hands-on experience with PyTorch, TensorFlow/Lite and familiarity with ML compilers like MLIR, TVM, ONNX Runtime.

Responsibilities

• Lead research and define NDK toolchain feature roadmap aligned with NPU hardware and AI product strategy.
• Evaluate quantization, pruning, distillation, and compression methods for constrained hardware targets.
• Prototype and benchmark toolchain concepts; demonstrate accuracy-performance trade-offs for roadmap prioritization.
• Translate hardware capabilities into software toolchain requirements and optimization opportunities.
• Collaborate with Edge AI software and AI Architecture teams; document specifications for implementation.

Skills

Applied ML

Edge AI

Quantization

Model compression

Knowledge distillation

PyTorch

TensorFlow Lite

MLIR

TVM

ONNX Runtime

RISC-V

FPGA prototyping

Benchmarking

Leadership

Education

Bachelor's or Master's in CS/EE/CE

PhD preferred in ML/optimization/architecture

Tools

MLIR

TVM

ONNX Runtime

PyTorch

TensorFlow Lite

Job description

OmniVision Technologies Singapore Pte Ltd in Singapore seeks a senior ML engineer to drive applied research for the NDK roadmap, focusing on quantization, pruning, distillation, and on-device inference within Edge AI compute solutions.

You will bridge the AI Architecture and Software (Edge AI) teams, prototype ML algorithms, benchmark performance, and translate hardware constraints into software requirements while engaging with the global edge AI community.