Edge AI Systems Engineer - Lightweight ML & Embedded

TetraMem - Accelerate The World; San Jose (CA); On-site; USD 110,000 - 250,000; Full time

Job summary

TetraMem is seeking an experienced ML Engineer to develop and deploy lightweight edge AI models, with emphasis on audio processing. You will optimize models for embedded platforms such as FPGA and custom ASICs, collaborating with hardware teams to productionize solutions.

The role requires deep ML expertise (PyTorch, TensorFlow, JAX) and strong software skills (Python, C/C++), plus a track record of optimizing for latency, power, and size.

Qualifications

• 5+ years of experience in ML, or PhD in related field
• Expertise in edge AI and lightweight model deployment
• Proficiency with ML frameworks such as PyTorch, TensorFlow, JAX

Responsibilities

• Develop, optimize, and deploy lightweight ML models for edge AI, esp. audio
• Implement ML models on embedded platforms (FPGA, ASIC)
• Collaborate with hardware/software teams to productionize ML models
• Research state-of-the-art ML techniques to improve efficiency, latency, and power
• Improve inference efficiency and model compression (quantization, pruning, distillation)
• Provide mentorship to junior engineers and publish findings when applicable

Skills

Edge AI

Model optimization

Python

C/C++

PyTorch

TensorFlow

Education

PhD in Computer Science or Electrical Engineering

Tools

ONNX

TensorRT

TFLite/LiteRT

ncnn

CoreML

Job description

TetraMem is seeking an experienced ML Engineer to develop and deploy lightweight edge AI models, with emphasis on audio processing. You will optimize models for embedded platforms such as FPGA and custom ASICs, collaborating with hardware teams to productionize solutions.

The role requires deep ML expertise (PyTorch, TensorFlow, JAX) and strong software skills (Python, C/C++), plus a track record of optimizing for latency, power, and size.