Referso Jobs

Own the optimization pipeline for the models you ship
Apply quantization, weight sharing, pruning, and distillation
Do low-level performance work: write and tune WebGPU compute shaders and native kernels
Profile with browser and platform tools and eliminate bottlenecks
Build parts of the integration between the ML runtime and the game engine

Skills

machine learning on-device optimization quantization model export ONNX Runtime WebGPU Metal Vulkan CUDA Python

Working Student (f/m/d) for Edge AI Technology Scouting and Evaluation

NXP Semiconductors · Posted Nov 5, 2026

Open

Munich, Bavaria, Germany
Hybrid
Part-time · Intern
€19–€19 per hour

Apply with RefersoAI Apply on careers page

Assist the Edge AI Tooling & Methodologies team with technology scouting, evaluation, and reporting on emerging Edge AI solutions.

Compensation

An attractive hourly wage of €19.40

Responsibilities

Research emerging technologies and industry trends
Analyze and compare open-source frameworks and commercial offerings
Create technical reports and comparison studies
Collaborate with engineering and product teams to identify promising technologies

Requirements

Master’s degree in Computer Science, Artificial Intelligence, Machine Learning, or a related field
Nice to have: Python
Nice to have: Linux
Nice to have: Git
Nice to have: ONNXRuntime

Skills

Python Linux Git ONNXRuntime TFlite Executorch Llama.cpp

AI Phone - On-device AI / ML Systems Engineer

Bjak · Posted Nov 4, 2026

Open

India

Apply with RefersoAI Apply on careers page

Engineer responsible for evaluating, benchmarking, and integrating on-device AI/ML models into Android applications and system services, optimizing performance and power usage, and developing hybrid local/cloud routing mechanisms.

Responsibilities

Evaluate suitable open-weight and commercially available models for on-device execution
Benchmark model performance on target mobile hardware
Integrate models into Android applications and system services
Optimize inference latency, memory consumption and power usage
Evaluate quantization, compression and model distillation techniques

Requirements

Nice to have: on-device LLMs
Nice to have: Qualcomm QNN
Nice to have: MediaTek NeuroPilot
Nice to have: ONNX Runtime
Nice to have: LiteRT

Skills

Python C++model quantization performance optimization neural network inference hardware constraints

AI Phone - On-device AI / ML Systems Engineer

Bjak · Posted Nov 4, 2026

Open

Seoul, Seoul, South Korea

Apply with RefersoAI Apply on careers page

The mission is to build proactive applications and devices that bring intelligence into daily conversations, coordination, and workflows with minimal prompting, focusing on on-device AI/ML systems.

Responsibilities

Evaluate suitable open-weight and commercially available models for on-device execution
Benchmark model performance on target mobile hardware
Integrate models into Android applications and system services
Optimize inference latency, memory consumption and power usage
Evaluate quantization, compression and model distillation techniques

Requirements

Nice to have: on-device LLMs
Nice to have: Qualcomm QNN
Nice to have: MediaTek NeuroPilot
Nice to have: ONNX Runtime
Nice to have: LiteRT

Skills

ML systems or inference engineering deploying and optimizing models Python C++neural network inference model quantization

AI Phone - On-device AI / ML Systems Engineer

Bjak · Posted Nov 4, 2026

Open

Remote, United Kingdom
Remote

Apply with RefersoAI Apply on careers page

The role involves building proactive AI applications and devices that bring intelligence into daily workflows, focusing on on-device AI/ML systems.

Responsibilities

Evaluate suitable open-weight and commercially available models for on-device execution
Benchmark model performance on target mobile hardware
Integrate models into Android applications and system services
Optimize inference latency, memory consumption and power usage
Evaluate quantization, compression and model distillation techniques

Requirements

Nice to have: On-device LLMs
Nice to have: Qualcomm QNN
Nice to have: MediaTek NeuroPilot
Nice to have: ONNX Runtime
Nice to have: LiteRT

Skills

ML systems Inference engineering Python C++Neural network inference Model quantization Performance optimization

Principal Machine Learning Engineer

Principal Machine Learning Engineer

Compensation

Responsibilities

Requirements

Skills

Benefits

Staff Machine Learning Engineer

Compensation

Responsibilities

Skills

Working Student (f/m/d) for Edge AI Technology Scouting and Evaluation

Compensation

Responsibilities

Requirements

Skills

AI Phone - On-device AI / ML Systems Engineer

Responsibilities

Requirements

Skills

AI Phone - On-device AI / ML Systems Engineer

Responsibilities

Requirements

Skills

AI Phone - On-device AI / ML Systems Engineer

Responsibilities

Requirements

Skills

Benefits

Benefits

Executorch jobs

Compensation

Responsibilities

Requirements

Skills

Benefits

Compensation

Responsibilities

Skills

Compensation

Responsibilities

Requirements

Skills

Responsibilities

Requirements

Skills

Responsibilities

Requirements

Skills

Responsibilities

Requirements

Skills

Benefits

Benefits